diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index 20004291aacfa6744c64d8bdf192378d39ff1d78..c2a43b4627f67ff727e6836f1430bfdc77c49296 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,18 @@ --- +language: +- en +- fr +- it +- pt +- hi +- es +- th +- de license: llama3.3 +base_model: meta-llama/Llama-3.3-70B-Instruct +base_model_relation: quantized +library_name: mlc-llm +pipeline_tag: text-generation --- + +4-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/). diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..d9e7e08f5c8e277065c653a7c72987d064f55208 --- /dev/null +++ b/config.json @@ -0,0 +1,5 @@ +{ + "quantization_config": { + "bits": 4 + } +} diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..2fbc183d50361805c9aeef61bdd2780d323c8170 --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,11583 @@ +{ + "metadata": { + "ParamSize": 805, + "ParamBytes": 36381212672.0, + "BitsPerParam": 3.4891900844756822 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 525336576, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 1024, + 128256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 525336576, + "byteOffset": 0 + } + ], + "md5sum": "efc3106ddacb59cc63dedebceab79b3b" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.78.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f0f4c1bbe9d71c7ef988e25eeee9eabe" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.78.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "6c82188aebff88551e29a6b5ae10cb09" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.79.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "82a6c16e1ffd5b74b159454093bb40a3" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.79.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "691a8d358fc2498eb62b3251ead7bfa5" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 31145984, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 64, + 128256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16416768, + "byteOffset": 0 + }, + { + "name": "model.layers.78.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 16416768 + }, + { + "name": "model.layers.78.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 16433152 + }, + { + "name": "model.layers.78.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 20103168 + }, + { + "name": "model.layers.78.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 27443200 + }, + { + "name": "model.layers.79.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 27459584 + }, + { + "name": "model.layers.79.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27475968 + } + ], + "md5sum": "3ea3dacf500c82d95cd81b4e3a08b3ed" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.79.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b7b732285d93794cac02997f96687c9b" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.79.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "7a0770ff2c7492047f6df289484d5985" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 525336576, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 128256, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 525336576, + "byteOffset": 0 + } + ], + "md5sum": "a47c1e9f873f5e3ec3f2bb7b1ace4480" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "4385b3eec159eb8924eb4fcd346fc255" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "7ee41f1a02f5cb0a9586786924d464a3" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 29835264, + "records": [ + { + "name": "model.layers.79.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.79.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.79.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.79.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.norm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 128256, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16416768, + "byteOffset": 9732096 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26148864 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 26165248 + } + ], + "md5sum": "2d36940bd342952ab1e17bf6ae296e62" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "100d3b723e384ff71dc7d5baff34a694" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ce769fee827e0187f1428d62348f045d" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "a043ce0c03d7b7f9d5e4a9585eb51373" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "de96c52b3a6dc874a12911bcc0d98771" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "fb23c59e2957426ad32587559cf28b22" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "3551358a1946ef0074b4605d9ffa4067" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b62d95a534623dbb7ac2c84ea7d29b23" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0a29b72bad1c188445153a0b661b64e1" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "65fa70f072b0577178fd2fce14a45ca7" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "614a9bf986a06bcc12ec9f59bd72421f" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "889aafd863ecca880ed554e9279dd026" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "57941c2fce2274ddf4a2b7f2c2e6df74" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "7451d3d24d72f32899790ad307538bba" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1039cc5b1ccdda383f4f4316e590a83a" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "50298e6be3a446f37e4fd110a5699eba" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "3b32dbe29af4c796bb24ee5ae4f51afc" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "98e63771f5e83e04e55069cbed0e9ae2" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "41104d399265239dc5d047d194bd9b14" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "793249139ad20058ab7c395c391e7536" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "46a995045a44d4962322396a02dbd5ef" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "78144c31e3e668af571b7e30477bdb59" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a8453fe0db162b4d604ad762a666c4a2" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "bfeafa54bb3c4c70e22d93ae9430adb6" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "e62afa705feb6818f77619a2a921f9d3" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d1d8efe3012ed60844b4a0602572d610" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4c88b0a5942e317982979e204843c59c" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "984bb2fa174ee0ec7ca4d238e8e58de4" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d8004a04594fb4f93cc919fc1e38b18f" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "69660c235aba311830dfe221c826a8dc" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "00b0d67ed1c3216b7f2ef4efd9681199" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 32833536, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 23117824 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 30457856 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 31768576 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 32817152 + } + ], + "md5sum": "e1136d6f47e208d1a1bfd95151318a11" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "0f33a6ab3b71bc9aacf3c15be052be85" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "18295a0304e2e1f0dad1c2935c486d00" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "a45a0dd247f8e9fa007932f73f6ff091" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e9fda5af930b15c0a4c9e5b77bd9e52a" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b1d23810cfb46332bad2a28c51840249" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "20e4025397f0d47dd2c94e16ba7a5bbb" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f5c39e4226eda9d97f959fcd71c944fb" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 28147712, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11042816 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11059200 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 11075584 + }, + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 14745600 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22085632 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 22102016 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 23412736 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24461312 + }, + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24477696 + } + ], + "md5sum": "8dc8251fd174a0c1bb043d33bb5a9b42" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a1f04e6228eb82b9709c87ed1aeecf34" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4080a024ee0ab24db33e6bdc82097c28" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "bb2ec39b7edd5c070a4d2acf0ce9b78a" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5fdfb4a2b265d832884bbdb8a9a14508" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "fe057ccf6c44914fe0021b5c6372fe88" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "606fbaf9faf8b7c3bd581ea6a444cb59" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f76543829ef99acd43bbdbc43e60b93a" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4a97993ef8a39f32336a70ee05ffae6f" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12075008 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 12091392 + }, + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 15761408 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "8d7b65ead90968f0f910c15a8535a759" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "09000f4734aa59234d884d78d7a74dbf" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "df4511a552353d57772dc6d33a0e72e8" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "5a2c2c8756b63a6981c9fda187cff868" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "71180ee9865c30d64cc923bc25d34139" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "aa4fef90eea384a99028b2271870f9ef" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5202b45f83901d0a5fa7b60a4c5ba713" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "4a9c1db75185802347e719aa8638bf2b" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6f6e57181c85b5297733ee699ced5788" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f53899e3b29c464c14cfea785c624c19" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 28114944, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24444928 + } + ], + "md5sum": "040234b169c79139223fce607dcabae1" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "544bf2d99b976c3c74a08035b1ea1701" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "0265bc844a93fb947e0223506d3266a2" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "169a492d05e2bd31d5a42ac72bd50fc4" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "13b93ff5bf62570bf961d17684f9db5e" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c6eae21b9453cb2cbd7b325054d75d51" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6042d793933474a52ef17eb00faf05a6" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4a840f4ebf6d2d422ea6404cf1ef473f" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5a4caf461a3a17a698a1c830ba75ca9e" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 32817152, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 7356416 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 8404992 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 8421376 + }, + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 12091392 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19431424 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 19447808 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 20758528 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 21807104 + }, + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 25477120 + } + ], + "md5sum": "c3c42b6a573ac083588527d2e4bb974c" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "fc68252df9a54a8c54748c4cbadc1128" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b19dcb84d3a711d0f300689c33222811" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "e56665e734fc5bc89baba60aaf2bc4c8" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "6460e5c29059f928a5be5d09db20ed2b" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "39600ba0c682955e4a59f80534874e64" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6742af1276340847593280374935a847" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "a1273030b6fd8143f32744582f39d424" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "db4355d904eaafd5b9bd0eef8e668b50" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a94e9e9f2ba68e45bb1289dac7e18882" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c9fcbc09f634fa26c107756885ab3c1e" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 29196288, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 0 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 1310720 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2375680 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2392064 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2408448 + }, + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6078464 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13418496 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 13434880 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 14745600 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15794176 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 15810560 + }, + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 19480576 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26820608 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 26836992 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 28147712 + } + ], + "md5sum": "775f352bdb8343469348c7d8c57b0f2a" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "49821409c07857472c077aa8541f77dd" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a6c57e9535cfae39a02ae7743443ccba" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d9ee2e6bcb1dccba7a1ef83d808ed315" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "bca77c4d3588a836ba18fc3150ccf477" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "678c9503345c2610120846a8418e0994" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1312d7ff11672394c1e3791b1b49c159" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "bd3eb63d620a1b618fdc9cf94ce1ba97" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "7305c639ae0f0d6f10eb7af4ff3a1cd3" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "144a0f47337e53060579487008f88f96" + }, + { + "dataPath": "params_shard_99.bin", + "format": "raw-shard", + "nbytes": 30490624, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9715712 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13402112 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 13418496 + }, + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 17088512 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 24444928 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 25755648 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26804224 + }, + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 26820608 + } + ], + "md5sum": "6af66fff8c25cbc3a779adb6bd289ce7" + }, + { + "dataPath": "params_shard_100.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1524450c2143ee1c0d6b79c2a9b9f5d2" + }, + { + "dataPath": "params_shard_101.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "78c6ebc2e67abb4d16b5a039232f842f" + }, + { + "dataPath": "params_shard_102.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "dbad2f2cc8977298995058c08181a7b3" + }, + { + "dataPath": "params_shard_103.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ee07abb8d6fabfebb4b8b152e6e15eeb" + }, + { + "dataPath": "params_shard_104.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "4eb85ac033787a4c2159402efa80c281" + }, + { + "dataPath": "params_shard_105.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "29db328ab01159708c9891621338e157" + }, + { + "dataPath": "params_shard_106.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c39154270b05978638d4843ee0e0344a" + }, + { + "dataPath": "params_shard_107.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "13ae89b6eb3841f742725a5afd64adad" + }, + { + "dataPath": "params_shard_108.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12075008 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 12091392 + }, + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 15761408 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "82aa24a1e61a70d3e6b09ce280402b1d" + }, + { + "dataPath": "params_shard_109.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9c945b53dbd0d3c5add65f01f0d4f4f1" + }, + { + "dataPath": "params_shard_110.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "0432b0263f7c2906e68b05e882676724" + }, + { + "dataPath": "params_shard_111.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ffee73ab639410bc1a4197c3e754e60e" + }, + { + "dataPath": "params_shard_112.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "305e4189e3156bbe1a985de3e8ae4e4d" + }, + { + "dataPath": "params_shard_113.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.28.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b7dec7d3a4e9daaa4a2e8378a85e36cb" + }, + { + "dataPath": "params_shard_114.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.28.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "9b016f92ba96ec9101933e9dbf813ba3" + }, + { + "dataPath": "params_shard_115.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.29.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9315400cc2d54073944537fb0bbf984e" + }, + { + "dataPath": "params_shard_116.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "41364bb3bc1ea9c2471d1f8836cb3ddf" + }, + { + "dataPath": "params_shard_117.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f381f8516a6273366fb84e90f43bf903" + }, + { + "dataPath": "params_shard_118.bin", + "format": "raw-shard", + "nbytes": 28114944, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.28.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24444928 + } + ], + "md5sum": "6494ff689575c3f2ed8002e20e32dbd5" + }, + { + "dataPath": "params_shard_119.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.29.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a419621b5f1485119ff11cd1e9636951" + }, + { + "dataPath": "params_shard_120.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "7291155fa45682fa787167cc9f2d3882" + }, + { + "dataPath": "params_shard_121.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "d6ff6296871fcf8527ba001a7bf24c8a" + }, + { + "dataPath": "params_shard_122.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "80f9379cfc5e801f36d604f9b9319162" + }, + { + "dataPath": "params_shard_123.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.30.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "7a6d05d1b5f2854cff6d0f1d7e1e7e62" + }, + { + "dataPath": "params_shard_124.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c0e672721937e600b3b35eb856dddcb1" + }, + { + "dataPath": "params_shard_125.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "6c16df9943a4ebb5b730bc19fe28b0c8" + }, + { + "dataPath": "params_shard_126.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "987eb242432ec8f0479fefd8e866e09c" + }, + { + "dataPath": "params_shard_127.bin", + "format": "raw-shard", + "nbytes": 32817152, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 7356416 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 8404992 + }, + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 8421376 + }, + { + "name": "model.layers.30.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 12091392 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19431424 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 19447808 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 20758528 + }, + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 21807104 + }, + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 25477120 + } + ], + "md5sum": "426c520266622e5d15fb1651f66a5e4c" + }, + { + "dataPath": "params_shard_128.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4888ed0f82754fca63f71ffb2c69b3c4" + }, + { + "dataPath": "params_shard_129.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "47d7e9db833b9ab3b290a750c9257f88" + }, + { + "dataPath": "params_shard_130.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "752542d813cf6be26baee33022fa5acf" + }, + { + "dataPath": "params_shard_131.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.32.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b1c1ab41d5d6e180a8f88ee952daa596" + }, + { + "dataPath": "params_shard_132.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.32.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "acc6bba2675939de62762a1b73659edc" + }, + { + "dataPath": "params_shard_133.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d5d8ed37b4247f7b8a5f4e21a3b26216" + }, + { + "dataPath": "params_shard_134.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0101cd0b12a1e6d467ecc87e1d784cad" + }, + { + "dataPath": "params_shard_135.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.33.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8c38691f19f20fa47ff02960f64d80a2" + }, + { + "dataPath": "params_shard_136.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.33.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "8037667627a6d0c1ad9669f36b8ee26e" + }, + { + "dataPath": "params_shard_137.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "8d3f7f14332ffe95b31e59e223f82746" + }, + { + "dataPath": "params_shard_138.bin", + "format": "raw-shard", + "nbytes": 29196288, + "records": [ + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 0 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 1310720 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2375680 + }, + { + "name": "model.layers.32.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2392064 + }, + { + "name": "model.layers.32.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2408448 + }, + { + "name": "model.layers.32.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6078464 + }, + { + "name": "model.layers.32.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13418496 + }, + { + "name": "model.layers.32.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 13434880 + }, + { + "name": "model.layers.32.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 14745600 + }, + { + "name": "model.layers.33.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15794176 + }, + { + "name": "model.layers.33.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 15810560 + }, + { + "name": "model.layers.33.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 19480576 + }, + { + "name": "model.layers.33.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26820608 + }, + { + "name": "model.layers.33.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 26836992 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 28147712 + } + ], + "md5sum": "aca5f38988edce50ea6a3eae99226f78" + }, + { + "dataPath": "params_shard_139.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.34.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "0c4580d8bd87e7f95e4a143cd63cfd07" + }, + { + "dataPath": "params_shard_140.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.34.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "97e7104088c57b5f3b3303dba13865b6" + }, + { + "dataPath": "params_shard_141.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "e289dd5ecb42b9a0f930f0d4e9c250d5" + }, + { + "dataPath": "params_shard_142.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "10f100ac52f5757eb2b728c68e9355f2" + }, + { + "dataPath": "params_shard_143.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "d3b3799ed67550102eeb3bfbb1bca28d" + }, + { + "dataPath": "params_shard_144.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.35.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "bbbc3cffb83bb6fe9ddbf62233ece801" + }, + { + "dataPath": "params_shard_145.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.35.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "065a077328e4d41d562016297921e566" + }, + { + "dataPath": "params_shard_146.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b5e2f8e98516ac21eb7569fa25e7b5ac" + }, + { + "dataPath": "params_shard_147.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c6dcddecf68009b38d1999252898afd4" + }, + { + "dataPath": "params_shard_148.bin", + "format": "raw-shard", + "nbytes": 30490624, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.34.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.34.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.34.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.34.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9715712 + }, + { + "name": "model.layers.34.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.35.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13402112 + }, + { + "name": "model.layers.35.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 13418496 + }, + { + "name": "model.layers.35.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 17088512 + }, + { + "name": "model.layers.35.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.35.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 24444928 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 25755648 + }, + { + "name": "model.layers.36.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26804224 + }, + { + "name": "model.layers.36.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 26820608 + } + ], + "md5sum": "6ef8e5bd964970117dc5d6e0a01a39cc" + }, + { + "dataPath": "params_shard_149.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.36.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "35cc27d91fdf4eea013c573759e23e4b" + }, + { + "dataPath": "params_shard_150.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.36.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "0464f0fa4e942ce54831e9e4b1688d72" + }, + { + "dataPath": "params_shard_151.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.37.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "90196dcfecac89672d8c38b9b705beef" + }, + { + "dataPath": "params_shard_152.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.37.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "bb12d1e5234454a03748311c0246a978" + }, + { + "dataPath": "params_shard_153.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.37.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "4eba872b80b3d7e66f7a7e62d07482f6" + }, + { + "dataPath": "params_shard_154.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0e3cf563baa15d9846f56d2824f1028d" + }, + { + "dataPath": "params_shard_155.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "59c3a05d00074d919911330f16334d6a" + }, + { + "dataPath": "params_shard_156.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "eacf10d490f39659027c499c6a8ba57f" + }, + { + "dataPath": "params_shard_157.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.36.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.36.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.37.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + }, + { + "name": "model.layers.37.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12075008 + }, + { + "name": "model.layers.37.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 12091392 + }, + { + "name": "model.layers.37.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 15761408 + }, + { + "name": "model.layers.37.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.38.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.38.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "58f2bbc43a4b16b1340e0e5f1c9704f4" + }, + { + "dataPath": "params_shard_158.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.38.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8ba38d55eab9c15b5e778883cf0c870b" + }, + { + "dataPath": "params_shard_159.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.38.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "839fb5df9112e2687c074a75956e134f" + }, + { + "dataPath": "params_shard_160.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.39.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b10c7888d7630d36508f588a0858ade2" + }, + { + "dataPath": "params_shard_161.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "3bc144e809c5c35d420e03c30fbbed54" + }, + { + "dataPath": "params_shard_162.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.39.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "306a4b8f6df24c29b9e44bcd5fbebb10" + }, + { + "dataPath": "params_shard_163.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.39.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "10a61b69a103dd46afb045ae0315f2a8" + }, + { + "dataPath": "params_shard_164.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.40.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "6eea5bfe2633017b1a3aee2bb81f9f3f" + }, + { + "dataPath": "params_shard_165.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "8bb23f0444bdad8e8e3f8ed25ab5ceda" + }, + { + "dataPath": "params_shard_166.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "7e030aa17db562240405a48558e6c34e" + }, + { + "dataPath": "params_shard_167.bin", + "format": "raw-shard", + "nbytes": 28114944, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.38.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.38.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.38.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.39.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.39.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.39.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.39.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.39.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.40.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24444928 + } + ], + "md5sum": "b869edc132ea32a6ceca1e93dd017670" + }, + { + "dataPath": "params_shard_168.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d0aed7a743d28baf1b578bfe555de43d" + }, + { + "dataPath": "params_shard_169.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "15657fc42ac169166ab5cf5dd963b591" + }, + { + "dataPath": "params_shard_170.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "371484c65ce4d5c1c3d12ae2f424db6b" + }, + { + "dataPath": "params_shard_171.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6f86f9950ff469c496370473e71299cf" + }, + { + "dataPath": "params_shard_172.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a83e17d0d1146ae4fc6505f47a7251d3" + }, + { + "dataPath": "params_shard_173.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4b83f7eebd12fb8e7ee735ecec0892ab" + }, + { + "dataPath": "params_shard_174.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e184d7d3df9e13d4d0b8ad58ae83289b" + }, + { + "dataPath": "params_shard_175.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "066a8fa4b145b6de6cdee7d7939dfa35" + }, + { + "dataPath": "params_shard_176.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "7f02230ad739e3f5fed434c2a91a5490" + }, + { + "dataPath": "params_shard_177.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "84e1d3e08015441a481cfc02eba5f629" + }, + { + "dataPath": "params_shard_178.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "fb4a7d59332564b58235dda6d517839d" + }, + { + "dataPath": "params_shard_179.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "9da35b360eabada3b6dd38b17352afd1" + }, + { + "dataPath": "params_shard_180.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.40.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "02cf6419c596904d686e0e288ce6bb1f" + }, + { + "dataPath": "params_shard_181.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.41.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "de7b984ad7955161048b6a2bc958bca6" + }, + { + "dataPath": "params_shard_182.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "d243991ec4b39d99ce261d45bba12b20" + }, + { + "dataPath": "params_shard_183.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.41.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "abf8a8443532bd6a63dd39eddd4db052" + }, + { + "dataPath": "params_shard_184.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.41.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "abb9d14229fff58a864e69f8eec80913" + }, + { + "dataPath": "params_shard_185.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.42.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "0fe504c3605984f734a1f16a29b19600" + }, + { + "dataPath": "params_shard_186.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "20e78e49712e328c738a631f889fd057" + }, + { + "dataPath": "params_shard_187.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.40.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.40.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.40.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.40.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.40.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.41.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.41.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.41.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.41.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.41.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.42.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "ecff0cedc53f482417915b31ed357099" + }, + { + "dataPath": "params_shard_188.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.42.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "131bd6662958f626462f854c845a62ee" + }, + { + "dataPath": "params_shard_189.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.42.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c0861521b312f976a366a341f2f55fd1" + }, + { + "dataPath": "params_shard_190.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.43.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a21f906887923aa26be4bbd1e4db1dbf" + }, + { + "dataPath": "params_shard_191.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.43.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "23f4cb3fa929d99d1ce803a38f6019b0" + }, + { + "dataPath": "params_shard_192.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.43.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "cd3656d4c1d59da0eef07590a48e15f1" + }, + { + "dataPath": "params_shard_193.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.43.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e0782dc89eff0c95bdee2cbc1836837c" + }, + { + "dataPath": "params_shard_194.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.44.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ff2da1831b44abefb386e12d3849877e" + }, + { + "dataPath": "params_shard_195.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "d4d669ff2b9f6f571ecc1c5b7b53236e" + }, + { + "dataPath": "params_shard_196.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.42.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.42.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.42.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.42.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.43.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.43.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.43.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.43.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.43.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.43.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.44.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.44.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "0bd43d9d3ec96564bd65b733b263163e" + }, + { + "dataPath": "params_shard_197.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.44.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "44b787b949feb939fc1102d8fcfc0075" + }, + { + "dataPath": "params_shard_198.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.44.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3edabe9970a59ac05e0f4f795133837e" + }, + { + "dataPath": "params_shard_199.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.45.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "869e032ffd0e92c548e8143d4d651199" + }, + { + "dataPath": "params_shard_200.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.45.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b354d27297a08c7d533035baead6bbbf" + }, + { + "dataPath": "params_shard_201.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.45.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5b3a0d6ec346df64e1b64deb06a616e9" + }, + { + "dataPath": "params_shard_202.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.45.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d662f3bf4e25afc81a6db519b4206741" + }, + { + "dataPath": "params_shard_203.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.46.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "4d51ad6ed880a953b7832a42222e33cc" + }, + { + "dataPath": "params_shard_204.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "6161d23484f312fb9e19dfb147613c7c" + }, + { + "dataPath": "params_shard_205.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.44.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.44.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.44.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.45.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.45.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.45.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.45.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.45.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.45.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.46.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.46.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "a637354c5f16790fdb8a7f55fa995f3c" + }, + { + "dataPath": "params_shard_206.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.46.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c46f88d8a308d415107e8c743194ce89" + }, + { + "dataPath": "params_shard_207.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.46.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "98a14c1b9094e3ff35e3c7f322d6b212" + }, + { + "dataPath": "params_shard_208.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.47.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2f5ce60766952538e505ad0292a6678d" + }, + { + "dataPath": "params_shard_209.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.47.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "975037ea396501298bd06a91165f598c" + }, + { + "dataPath": "params_shard_210.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.47.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5efc86551db998594095c27e1c4a63f8" + }, + { + "dataPath": "params_shard_211.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.47.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "820cda566bb9290b0157cd0c50961602" + }, + { + "dataPath": "params_shard_212.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.48.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "84cfd7c70ffce96dc9a0c97b2c0af849" + }, + { + "dataPath": "params_shard_213.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.48.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "77fc7002c20c93b8550d79f81c1bd656" + }, + { + "dataPath": "params_shard_214.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.48.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d28beb31ba9c6ed750e127c6cc18f64b" + }, + { + "dataPath": "params_shard_215.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "d2114321d5a05301b0f5a79860874c85" + }, + { + "dataPath": "params_shard_216.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.46.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.46.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.46.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.47.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.47.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.47.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.47.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.47.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.47.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.48.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.48.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.48.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.48.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "a31d5873f54bf92ce026e26ec009caf0" + }, + { + "dataPath": "params_shard_217.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.49.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ce5c891a27e2d866529d026a7b8ea715" + }, + { + "dataPath": "params_shard_218.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.49.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f87b7e294822bf75c0c8204882740d3c" + }, + { + "dataPath": "params_shard_219.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.49.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "be4ee369ca04668da4a6e70371c78e3b" + }, + { + "dataPath": "params_shard_220.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.49.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "bae0c41d9a6073fed8bdbc65f8983b97" + }, + { + "dataPath": "params_shard_221.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.50.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "326c269552facaae77cacb415ea91edf" + }, + { + "dataPath": "params_shard_222.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.50.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "21454f145b1bf10fbfc7c63c542bc01e" + }, + { + "dataPath": "params_shard_223.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.50.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1ed4fe8748ffc1f88026fe6c314263ba" + }, + { + "dataPath": "params_shard_224.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.50.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "8590abad4ff24c9655c735d3d9406c5e" + }, + { + "dataPath": "params_shard_225.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.48.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.49.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.49.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.49.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.49.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.49.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.49.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.50.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.50.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.50.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.50.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.50.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "faf7c24f2a73bd25dc89f127d4927881" + }, + { + "dataPath": "params_shard_226.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.51.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "bc0d546006993f57970e19b9a0d491b8" + }, + { + "dataPath": "params_shard_227.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.51.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "e766212de8e906345e0a09fa6969ae82" + }, + { + "dataPath": "params_shard_228.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.51.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "38e2f8d68a2bc80b7184b5e56a2c7d42" + }, + { + "dataPath": "params_shard_229.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.51.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "94f89c6df9dc6dc076452b0cf18ab1c3" + }, + { + "dataPath": "params_shard_230.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.52.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "625f2f1652e66e8dddf82e5bc973aa7e" + }, + { + "dataPath": "params_shard_231.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.52.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f426017f65c21dd1a7835f774ae5e667" + }, + { + "dataPath": "params_shard_232.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.52.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "0145a2d3e1fa6d262e8752894a4f37fd" + }, + { + "dataPath": "params_shard_233.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.52.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "01e2cbfac66e640151e013495dec1e44" + }, + { + "dataPath": "params_shard_234.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.53.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "fa085e1a2e408669b4e1a46b26754f1b" + }, + { + "dataPath": "params_shard_235.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "5317b2fb671df0a7ded370370b63428e" + }, + { + "dataPath": "params_shard_236.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.50.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.51.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.51.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.51.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.51.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.51.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.51.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.52.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.52.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.52.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.52.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.52.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.52.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.53.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "6d616dfb8ac8f1b09268d25f1a88f23d" + }, + { + "dataPath": "params_shard_237.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.53.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "148f8f3f197eb033732c514e2a998072" + }, + { + "dataPath": "params_shard_238.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.53.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "17e88f2e18e5fe862c76c39eb111cbcc" + }, + { + "dataPath": "params_shard_239.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.54.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "dc5342fed2935e7df4f4477dfa6f1ec1" + }, + { + "dataPath": "params_shard_240.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.54.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "822d95295cc053c6af1895bf03bd2dfa" + }, + { + "dataPath": "params_shard_241.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.54.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8259931278983d562ca2bf6849145a81" + }, + { + "dataPath": "params_shard_242.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.54.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4da25ac2e0e78211acc6f75d4bafb2cb" + }, + { + "dataPath": "params_shard_243.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.55.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ea5adc2a02133bc0a238c7f714e0164a" + }, + { + "dataPath": "params_shard_244.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b288ec6a04ab1c93e2112f26db5ad758" + }, + { + "dataPath": "params_shard_245.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.53.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.53.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.53.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.53.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.54.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.54.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.54.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.54.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.54.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.54.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.55.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.55.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "29678b835e0e0e880047cac48d328f68" + }, + { + "dataPath": "params_shard_246.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.55.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "4ed9b577e2e70ff5243efb6cb2eca861" + }, + { + "dataPath": "params_shard_247.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.55.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6e341e41edaae2890ecad37ff33a008b" + }, + { + "dataPath": "params_shard_248.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.56.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "1ec1ab00fad29440d2ec9d4e7c92b837" + }, + { + "dataPath": "params_shard_249.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.56.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "df3700b56a076ca280d598868adadf48" + }, + { + "dataPath": "params_shard_250.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.56.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "cc96ba9b4c7da0ac3bc952e6de2ecc98" + }, + { + "dataPath": "params_shard_251.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.56.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "108a56d0feb417eb416c7eda6833290b" + }, + { + "dataPath": "params_shard_252.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.57.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "5f610474d5e23c36fa2ea39dd43ca97d" + }, + { + "dataPath": "params_shard_253.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "6672c0d53575df9a926812d306773c22" + }, + { + "dataPath": "params_shard_254.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.55.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.55.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.55.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.56.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.56.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.56.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.56.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.56.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.56.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.57.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.57.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "c8066ae3c171e67e6f4bb58c8a2171d0" + }, + { + "dataPath": "params_shard_255.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.57.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "23099955e9396e403c3cdc7312d14641" + }, + { + "dataPath": "params_shard_256.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.57.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "0391e4161a3448ee2d18900bf4752fc9" + }, + { + "dataPath": "params_shard_257.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.58.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "e4cd53b4621980583fb3d9b72425273b" + }, + { + "dataPath": "params_shard_258.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.58.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b061517e5e20e3905927daf381706048" + }, + { + "dataPath": "params_shard_259.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.58.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c7f15d2ba53ab8a1625930e203033e6c" + }, + { + "dataPath": "params_shard_260.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.58.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d47bb0b89343fc54384883182f3787bb" + }, + { + "dataPath": "params_shard_261.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.59.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "009f9f409ecf35e7cca953d31fc5e4e8" + }, + { + "dataPath": "params_shard_262.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.59.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "54be631b67c30c5ffff844a01cf266ff" + }, + { + "dataPath": "params_shard_263.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.59.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2369d0e5061fa8aaa9ffe928b9fc79ef" + }, + { + "dataPath": "params_shard_264.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "d44770b732069b58da6f9e5bc562f4df" + }, + { + "dataPath": "params_shard_265.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.57.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.57.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.57.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.58.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.58.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.58.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.58.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.58.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.58.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.59.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.59.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.59.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.59.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "ec121977e4aab4eaa1558adedd019937" + }, + { + "dataPath": "params_shard_266.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.60.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "612293323c0e0a6eefbbeefc777281e5" + }, + { + "dataPath": "params_shard_267.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.60.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c55d27a81d1c756c5052b5d4734647d7" + }, + { + "dataPath": "params_shard_268.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.60.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "04961dc854c5d1f73d94c8cc9cd46a04" + }, + { + "dataPath": "params_shard_269.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.60.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6c29177817262823a815b71a2bb29bd7" + }, + { + "dataPath": "params_shard_270.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.61.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "1c0885b3666ee7e6bc05b3229b863ae5" + }, + { + "dataPath": "params_shard_271.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.61.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4fc529693ba7335230a6fb303909710b" + }, + { + "dataPath": "params_shard_272.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.61.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "66795c40b62f08e3163985458255a12c" + }, + { + "dataPath": "params_shard_273.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.61.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "75c7a34e14c405dd9bba228a90761c0e" + }, + { + "dataPath": "params_shard_274.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.59.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.60.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.60.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.60.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.60.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.60.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.60.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.61.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.61.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.61.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.61.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.61.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "440526a4ac65b9c2945115ae4bc4811c" + }, + { + "dataPath": "params_shard_275.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.62.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "78b11be7eae5b5d77a7e567b0cfd4f72" + }, + { + "dataPath": "params_shard_276.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.62.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "59ccf8307f9d36a9222a64cf7308ce5f" + }, + { + "dataPath": "params_shard_277.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.62.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "00c6d63a0c757034cd0bf08bf30c6e72" + }, + { + "dataPath": "params_shard_278.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.62.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "87040d661a7473b9afd3211256409fb8" + }, + { + "dataPath": "params_shard_279.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.63.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "4b1e3d4c0d981a61ea986e79bc4ba74f" + }, + { + "dataPath": "params_shard_280.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.63.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "60f549891543da6c3935268220156bd8" + }, + { + "dataPath": "params_shard_281.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.63.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e3f15b5bcd22328294688d6ca92c1cd0" + }, + { + "dataPath": "params_shard_282.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.63.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "de07dc2b723964eb518c588b5fc88dae" + }, + { + "dataPath": "params_shard_283.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.64.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "8af8b538de176176fbe6980635864dee" + }, + { + "dataPath": "params_shard_284.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.64.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c1e7ad631336c0a2740227ee701102cb" + }, + { + "dataPath": "params_shard_285.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.61.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.62.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.62.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.62.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.62.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.62.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.62.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.63.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.63.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.63.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.63.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.63.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.63.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.64.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "2085a496419dbc282a9cdb57186d46c8" + }, + { + "dataPath": "params_shard_286.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.64.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a529b38c80c7455f450fd6715e06d564" + }, + { + "dataPath": "params_shard_287.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.64.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c2b652759234e15559622136d1e1ec6d" + }, + { + "dataPath": "params_shard_288.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.65.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "37821b9ea7181877b82c69cc49239bf6" + }, + { + "dataPath": "params_shard_289.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.65.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "eb534f3d5fb116e243693b1175d55f6b" + }, + { + "dataPath": "params_shard_290.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.65.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "225cc0d36a2124d904bda6be43b6a474" + }, + { + "dataPath": "params_shard_291.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.65.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "00ffb9d52f56b665178e54b17c204aec" + }, + { + "dataPath": "params_shard_292.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.66.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "3feb900219b3dca1411934efa2873982" + }, + { + "dataPath": "params_shard_293.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.66.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "905256fdd972160ab5e12aca3dda37ee" + }, + { + "dataPath": "params_shard_294.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.64.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.64.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.64.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.64.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.64.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.65.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.65.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.65.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.65.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.65.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.65.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.66.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.66.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "f5510d4b485739fe945aae2798131b7f" + }, + { + "dataPath": "params_shard_295.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.66.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "987b534e7e2eba2916af3e09418592c7" + }, + { + "dataPath": "params_shard_296.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.66.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c5c3348705537ce45981d35ff6b73d91" + }, + { + "dataPath": "params_shard_297.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.67.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "440753134ca9c4965aabb7e0a0c68041" + }, + { + "dataPath": "params_shard_298.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.67.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b3d54baafae9e757d9de5ecd1cf1be9a" + }, + { + "dataPath": "params_shard_299.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.67.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1e706ab5e9cbd4472d8e1fa4a3d36d21" + }, + { + "dataPath": "params_shard_300.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.67.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b310a6409f1cb4e522f26cf7b9ee1ecb" + }, + { + "dataPath": "params_shard_301.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.68.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c0c5e379b2f9c075ecbcadc55c166bb8" + }, + { + "dataPath": "params_shard_302.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.68.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "18924bd455627fabd7c56933bd4d58b7" + }, + { + "dataPath": "params_shard_303.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.66.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.66.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.66.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.66.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.67.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.67.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.67.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.67.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.67.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.67.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.68.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.68.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "674e5363fbd4b1bbfae6afc02c0bab05" + }, + { + "dataPath": "params_shard_304.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.68.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "7b6e3c701f30cc50c0e5e97e614d7daf" + }, + { + "dataPath": "params_shard_305.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.68.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "7675816e830817ec8645512a0510d9b5" + }, + { + "dataPath": "params_shard_306.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.69.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "20898edbd38f555b768b6d36d9807edd" + }, + { + "dataPath": "params_shard_307.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.69.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c6226876933f4be803f67f4b172d94d1" + }, + { + "dataPath": "params_shard_308.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.69.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "de6b601b73c730d42854d0c924b20c99" + }, + { + "dataPath": "params_shard_309.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.69.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "403ccf08166925c633870d6a41f52c3d" + }, + { + "dataPath": "params_shard_310.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.70.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "92f1f106ada320aaac80b07d76df0a4e" + }, + { + "dataPath": "params_shard_311.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.70.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e583d7b78ba0fe8b9f8b242590b29211" + }, + { + "dataPath": "params_shard_312.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "bcf778aed2fa826f4bdefb02844f76ba" + }, + { + "dataPath": "params_shard_313.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "eda62d2ce10877684cf844bdf0ddad75" + }, + { + "dataPath": "params_shard_314.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.68.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.68.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.68.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.68.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.69.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.69.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.69.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.69.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.69.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.69.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.70.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.70.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "c79e757bbd33e129f8bec962cfec8ff6" + }, + { + "dataPath": "params_shard_315.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e21968683bb7ccbd483782d326c396dc" + }, + { + "dataPath": "params_shard_316.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d5fcd267cf7c7705ebabbcb43ed7b2b3" + }, + { + "dataPath": "params_shard_317.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "fc435d6f1449d162293d860c04449199" + }, + { + "dataPath": "params_shard_318.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1edf032d4f95afaa7210fc07b5c4f00e" + }, + { + "dataPath": "params_shard_319.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d9d6b3e2a89beabe34373c4ac1567cac" + }, + { + "dataPath": "params_shard_320.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2fe53906ccf84163c22f0b3b7ce8564a" + }, + { + "dataPath": "params_shard_321.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "051ce37229e9e0646866093d82c60c5a" + }, + { + "dataPath": "params_shard_322.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "430e468b7fa6bf4586de0378681a1e8d" + }, + { + "dataPath": "params_shard_323.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.70.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "592cdd4a7e431cf98d6e7bd887b31ea1" + }, + { + "dataPath": "params_shard_324.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.70.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "63f15cbdf806d71ccd1609a32a35df42" + }, + { + "dataPath": "params_shard_325.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 7356416 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 8404992 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 8421376 + }, + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 12091392 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19431424 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 19447808 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 20758528 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 21807104 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25477120 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26787840 + }, + { + "name": "model.layers.70.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 27836416 + }, + { + "name": "model.layers.70.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "49cae41357f1420cfda1888da37d17bb" + }, + { + "dataPath": "params_shard_326.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.71.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "31bb9486a24e3d20b79df05f53397695" + }, + { + "dataPath": "params_shard_327.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.71.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4381e06a3f4fc5fac633b3da3d417c1c" + }, + { + "dataPath": "params_shard_328.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.71.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b36afdb4c72eac175fbdba8688102d60" + }, + { + "dataPath": "params_shard_329.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.71.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c1d4e7026cd468e1d9e13685157c5531" + }, + { + "dataPath": "params_shard_330.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.72.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "3a666ac0cdf78685cb146fdb65b13cf4" + }, + { + "dataPath": "params_shard_331.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.72.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "3f9461f89d889b355db9265c1b0ee666" + }, + { + "dataPath": "params_shard_332.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.72.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "2a0d0725639c30b0657cb466faf48a27" + }, + { + "dataPath": "params_shard_333.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.72.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c96c7e2802fb5650095f8a7e93a81404" + }, + { + "dataPath": "params_shard_334.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.70.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.70.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.71.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.71.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.71.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.71.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.71.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.71.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.72.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.72.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.72.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.72.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.72.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "a578975072553aed6063a7f7028223e6" + }, + { + "dataPath": "params_shard_335.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.73.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "112ab2021e978f5461fc22599895cc76" + }, + { + "dataPath": "params_shard_336.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.73.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c33238134d2aa810f2489c7ccd77301c" + }, + { + "dataPath": "params_shard_337.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.73.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b4ce5b39157f9e201c0bd59dcc4e293d" + }, + { + "dataPath": "params_shard_338.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.73.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ea25ef325d8a44c604418f9d6612fd08" + }, + { + "dataPath": "params_shard_339.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.74.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d5ebf26765b68e5e4cc643b1e1a5819f" + }, + { + "dataPath": "params_shard_340.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.74.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c7a16315ba0487ae1f39bb64e487546b" + }, + { + "dataPath": "params_shard_341.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.74.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "97a54401ee07519301e04fb80f10b005" + }, + { + "dataPath": "params_shard_342.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.74.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "9e2f09e0b5542a7e075958cb1066c046" + }, + { + "dataPath": "params_shard_343.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.75.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "4f57895f864eec5148658151624d6034" + }, + { + "dataPath": "params_shard_344.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.75.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "e60ad89c4504d6a2d0b43560cbbf6cc3" + }, + { + "dataPath": "params_shard_345.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.72.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.73.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.73.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.73.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.73.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.73.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.73.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.74.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.74.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.74.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.74.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.74.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.74.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.75.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "341e78bb64affbcfb62f72b952b028ab" + }, + { + "dataPath": "params_shard_346.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.75.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "519be956d6a68806e3528e45a2cab51c" + }, + { + "dataPath": "params_shard_347.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.75.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ee9bd106fdb01bd0d6ac1727a6b9208d" + }, + { + "dataPath": "params_shard_348.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.76.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f9280c0a29e70e58a16462875152a78b" + }, + { + "dataPath": "params_shard_349.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.76.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "ceeaa3d80147ca75b958ef8950047a0f" + }, + { + "dataPath": "params_shard_350.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.76.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "02e0bebf304877a4e211063b7a29515d" + }, + { + "dataPath": "params_shard_351.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.76.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "fb3dbe3364298b623ebd03d4ee6d2a57" + }, + { + "dataPath": "params_shard_352.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.77.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "656afbd1d0f42787d1afac5bf8e7257d" + }, + { + "dataPath": "params_shard_353.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.77.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "6eff3f0bd1ae368fcdab5d5bc14626f2" + }, + { + "dataPath": "params_shard_354.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.75.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.75.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.75.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.75.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.75.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.76.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.76.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.76.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.76.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.76.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.76.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.77.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.77.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "f6304ccf47bb4bbd4becc616b4d8b5fe" + }, + { + "dataPath": "params_shard_355.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.77.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "0c946a3d94e8425357eaab1c13e69cdc" + }, + { + "dataPath": "params_shard_356.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.77.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4f58b1e4634146431728644c5f7618ad" + }, + { + "dataPath": "params_shard_357.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.78.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e9cad67dd60ee8fe4b8dbd9ab31af877" + }, + { + "dataPath": "params_shard_358.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.78.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "60a49f6702b3a74d4b01fee27cd4f6c4" + }, + { + "dataPath": "params_shard_359.bin", + "format": "raw-shard", + "nbytes": 12075008, + "records": [ + { + "name": "model.layers.77.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.77.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.77.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.77.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.78.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.78.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + } + ], + "md5sum": "75236d0208d7a38c6d55c473aedfeb45" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..f717552ca2b7c950e8e6d6169647af2d40d10498 --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3072da5284fba515ac78cab512bb6443c7b2a00762305de98be0de430bf9d598 +size 525336576 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..b21789c9aa73510a9cd083d1c5945d2ce9c64f1b --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0d1eb7051fb893d535badf39e13e264f7c057563b9604c066dc5fb0351a2f8f +size 117440512 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..0cd7ef888f5e1e391bd4c01b0e3b1afc606fff3a --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b216bef743c91fb19b18fe9596d8bfaffd45d19b24c63faf2b37041750514ab +size 234881024 diff --git a/params_shard_100.bin b/params_shard_100.bin new file mode 100644 index 0000000000000000000000000000000000000000..e4567da2242aa720010e112012e15d1885ebfdd5 --- /dev/null +++ b/params_shard_100.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12243a8dc779426394fde3502fb57c82e763f60270100f2cf8ac914e8f0d8476 +size 41943040 diff --git a/params_shard_101.bin b/params_shard_101.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f52690abc2b8a4381ae922dd94ee4a82f0afc48 --- /dev/null +++ b/params_shard_101.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bfd896e743c0cbdd48708e5787c896831198a06a104817e57c0c2ae8cbe8374 +size 33554432 diff --git a/params_shard_102.bin b/params_shard_102.bin new file mode 100644 index 0000000000000000000000000000000000000000..c4eff02969b0c428da1fb5fdd8f0002b1e9866a4 --- /dev/null +++ b/params_shard_102.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3b7b74002acc9b90e482a34ae008fecde93c54d21c369a04ea57622d4970fb +size 41943040 diff --git a/params_shard_103.bin b/params_shard_103.bin new file mode 100644 index 0000000000000000000000000000000000000000..0a56c1f0ed1189088eade2cb1f32cc0d902f22be --- /dev/null +++ b/params_shard_103.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc11ba3dae1f7f08f57426e4074fa1e77657e50f8b4662d61ee383d98d28911f +size 33554432 diff --git a/params_shard_104.bin b/params_shard_104.bin new file mode 100644 index 0000000000000000000000000000000000000000..7a06e446021eda4eb98873ace1b6c3ce66541a33 --- /dev/null +++ b/params_shard_104.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5002ab0ae4996835cece7dcba77d7958b8b6a5e185722bf77d1590cf50cdcbfc +size 117440512 diff --git a/params_shard_105.bin b/params_shard_105.bin new file mode 100644 index 0000000000000000000000000000000000000000..c8d1ae2d5fa7f8d1449b47a75be9159e4b46abb4 --- /dev/null +++ b/params_shard_105.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f25e36662805d89327fa12cbd3788ab1badea5d7dd1fee7ce70b5f967d70145 +size 234881024 diff --git a/params_shard_106.bin b/params_shard_106.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ee5f33b99ac543fbad9f95ab05189c140879641 --- /dev/null +++ b/params_shard_106.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ef97e064ae6080c9dd6affeaf5a2c6e38bc564c4c639fc5f1a0ff18acc6a4a7 +size 117440512 diff --git a/params_shard_107.bin b/params_shard_107.bin new file mode 100644 index 0000000000000000000000000000000000000000..0b0397fac1f5711314272d70eb5f506e13c6a7b8 --- /dev/null +++ b/params_shard_107.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a512b10e5308234934de9026d59ccda9aca1136fe799ce25416dac88d1888aaf +size 234881024 diff --git a/params_shard_108.bin b/params_shard_108.bin new file mode 100644 index 0000000000000000000000000000000000000000..a6443b4bd442d318fba1c5639625ded0c64d5e4a --- /dev/null +++ b/params_shard_108.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ae3e96f50f890f0ff2109ed2bc015bae4499d9629f3da74cce1fa5db08faf4 +size 26804224 diff --git a/params_shard_109.bin b/params_shard_109.bin new file mode 100644 index 0000000000000000000000000000000000000000..df58b9ddef7fcebbed68774c47558641998e48bf --- /dev/null +++ b/params_shard_109.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04c58790979c3bcda33ec7ef56be5b6450b5d0b0aff5bac9c8a1eadbaf6f69f +size 41943040 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..cdb9660a8b58d01c6cc4e0eada35686096541e67 --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3303fb1d48da25706adf192bda07d892b9aa6a344d884937f1f228be3a0af63 +size 29835264 diff --git a/params_shard_110.bin b/params_shard_110.bin new file mode 100644 index 0000000000000000000000000000000000000000..b70d6f8da5b5fff20e2298c6f78d36f2f22e1261 --- /dev/null +++ b/params_shard_110.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7076b3c35fb3038475a07a54067ce95e28ae151532fcbcf2b122e93e6c60523d +size 33554432 diff --git a/params_shard_111.bin b/params_shard_111.bin new file mode 100644 index 0000000000000000000000000000000000000000..465516ad937f9099b10062651a1147eaeefdffa2 --- /dev/null +++ b/params_shard_111.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0590de947598b7152f900d4c7969b56eca4b6c21e9ce338b5122cb354e0070d9 +size 117440512 diff --git a/params_shard_112.bin b/params_shard_112.bin new file mode 100644 index 0000000000000000000000000000000000000000..575febe01845493acd7b3a4fa1e142f17f3d7c2f --- /dev/null +++ b/params_shard_112.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50595806ca1eb8f836766bd45a351934e49c6ef051ae20ed43f0510cb3e534f8 +size 234881024 diff --git a/params_shard_113.bin b/params_shard_113.bin new file mode 100644 index 0000000000000000000000000000000000000000..c94675c9b6923f81a85b106e1acf0dc193913f3b --- /dev/null +++ b/params_shard_113.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12fe95acfd92943fb836b0f4e7450daab9556004cff1cb140bfa36dc5e1a3828 +size 41943040 diff --git a/params_shard_114.bin b/params_shard_114.bin new file mode 100644 index 0000000000000000000000000000000000000000..6b97d150432ba3dcb1ddeec4bbbe99ff58686b9f --- /dev/null +++ b/params_shard_114.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59501a9a775af13182c59e2de4890687c75bf9df695a033d9eaf249f1f7659d1 +size 33554432 diff --git a/params_shard_115.bin b/params_shard_115.bin new file mode 100644 index 0000000000000000000000000000000000000000..57d26dcaf8422edc9e5cf098bfbe750fc48e2b05 --- /dev/null +++ b/params_shard_115.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3561ddf31860abaad73a32dce67dad989ef730852e24d9374cd37fd16338085c +size 41943040 diff --git a/params_shard_116.bin b/params_shard_116.bin new file mode 100644 index 0000000000000000000000000000000000000000..d502193e78da06b4167821ef4d9b34e329a277f5 --- /dev/null +++ b/params_shard_116.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67718daf8c6ce37306deb0ea46aeb828fa240548c53dd3e3abb664f10554188f +size 117440512 diff --git a/params_shard_117.bin b/params_shard_117.bin new file mode 100644 index 0000000000000000000000000000000000000000..adb0cb1ea2648ac9486567e1cf2a32afac99f37e --- /dev/null +++ b/params_shard_117.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62b3399eff2a6f698076bb3b1c6d6cc73ce7f8b5545ea08aefaeec6ba8637fe0 +size 234881024 diff --git a/params_shard_118.bin b/params_shard_118.bin new file mode 100644 index 0000000000000000000000000000000000000000..0785ca047c29aaec93136ea41582321f12733af1 --- /dev/null +++ b/params_shard_118.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f94d3a78deea15a28c68a462d138021f9660b89be5a246436a561a5b2230b451 +size 28114944 diff --git a/params_shard_119.bin b/params_shard_119.bin new file mode 100644 index 0000000000000000000000000000000000000000..45d18ab2deb4dedb8f1abcc9a479dc46bc0bd3de --- /dev/null +++ b/params_shard_119.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b363429ee9a5d7123973dae209cfbb76b6c4567fa1e38eed678dba4d918377 +size 33554432 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..cffb95d29a9565cbc69fc09330d11cdf8ea7c352 --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75d66885d4e89f5c78e408e1404c35baedde9268f17abfb6307eca159e5e3ff2 +size 41943040 diff --git a/params_shard_120.bin b/params_shard_120.bin new file mode 100644 index 0000000000000000000000000000000000000000..f5b38af73405f59fb78368a70e8d17d523abb895 --- /dev/null +++ b/params_shard_120.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5e131eb7ae5a8b5154826f6eab9e6cd22e3af8d4d1a9dd25b9afad8287c36c +size 117440512 diff --git a/params_shard_121.bin b/params_shard_121.bin new file mode 100644 index 0000000000000000000000000000000000000000..868cb3e30816397f28709d01f69f0706dc39604a --- /dev/null +++ b/params_shard_121.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc1c2e7f5e509d61716b8a86be1b3c1e17c8a310ea0b4c3c15cec7e6ce133862 +size 234881024 diff --git a/params_shard_122.bin b/params_shard_122.bin new file mode 100644 index 0000000000000000000000000000000000000000..07fc50ba3e38580e520a60cec8b86082538b7591 --- /dev/null +++ b/params_shard_122.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:420955e6bc702dd73f10df43b871a1c0277a6dde7289109792c34b91c0803261 +size 41943040 diff --git a/params_shard_123.bin b/params_shard_123.bin new file mode 100644 index 0000000000000000000000000000000000000000..575492181b786f91327fe2bc6830db2b9d4e9575 --- /dev/null +++ b/params_shard_123.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5187b46e0cabef0f9326a2ea1ea8c49258015ab0dd22fd736c7ebfe58fb5e7db +size 33554432 diff --git a/params_shard_124.bin b/params_shard_124.bin new file mode 100644 index 0000000000000000000000000000000000000000..0250d27c3f82a499d68e615e3124771d397d4e5f --- /dev/null +++ b/params_shard_124.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66c6cd54d551b966b2e6233cd36fb3ad47017fa1e444c88e5d8ce940129185c7 +size 117440512 diff --git a/params_shard_125.bin b/params_shard_125.bin new file mode 100644 index 0000000000000000000000000000000000000000..62b233b72dbdad5a16329f8ca869d3e8e8a4e235 --- /dev/null +++ b/params_shard_125.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d45024622788ff25403162bbbcb06d796a4a89b733f4fae1ff38b42190be825 +size 234881024 diff --git a/params_shard_126.bin b/params_shard_126.bin new file mode 100644 index 0000000000000000000000000000000000000000..67d6c47cbd06252f63fafeddc99dbb40e3f37ed9 --- /dev/null +++ b/params_shard_126.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:427216a2deb182ed4e7d3a62f42d1bf69b2fff25d378cb1d279d625856513398 +size 41943040 diff --git a/params_shard_127.bin b/params_shard_127.bin new file mode 100644 index 0000000000000000000000000000000000000000..69be863bf2a8e306131267045c9b34338296ba8b --- /dev/null +++ b/params_shard_127.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df279359f9a20a925b0f3e962b1ad9ae92b24583e6b0d78f4ac00ad5b54207fc +size 32817152 diff --git a/params_shard_128.bin b/params_shard_128.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b5c70c83e7fa79b507af54013a69d862279b1e5 --- /dev/null +++ b/params_shard_128.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1b79d3007158a7838b29074fa35c230535bfe37f217779b2603a80a1aa94920 +size 33554432 diff --git a/params_shard_129.bin b/params_shard_129.bin new file mode 100644 index 0000000000000000000000000000000000000000..63536fe0f615af991cae8e796f05aa91757a6213 --- /dev/null +++ b/params_shard_129.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3135f7646ddc31d6c4bab8dfbf8ce2ebd369eb1db3f58b8c89d2f9ad02728cd +size 117440512 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..b3757df7fb99a577f6a517b4ce8e820c6f875713 --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19de5b1dc7d1abfb18e813972deefdc046ba7933199f5df39fbead0ae4e08564 +size 33554432 diff --git a/params_shard_130.bin b/params_shard_130.bin new file mode 100644 index 0000000000000000000000000000000000000000..467bcf9f82bb7036eac529b6cf5912e6b06835ee --- /dev/null +++ b/params_shard_130.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2a96a500bc3454a46a5ffc8aeda3b18db2fd3c03b4330271b742ddf14624cc2 +size 234881024 diff --git a/params_shard_131.bin b/params_shard_131.bin new file mode 100644 index 0000000000000000000000000000000000000000..f71ddaf3283e0a9b50d7e2901a6dfffee38d0183 --- /dev/null +++ b/params_shard_131.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26877bc9083fc2e0669dfdc2a48391012f4875e9c3b62419ca8a9fb1deda16ed +size 41943040 diff --git a/params_shard_132.bin b/params_shard_132.bin new file mode 100644 index 0000000000000000000000000000000000000000..b8b5bd349fe70a6ceb7d4c471eb1c78939c2244f --- /dev/null +++ b/params_shard_132.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e2c15fcc1aca1d498f36689290db0847bee11539f7d18b089f5d5d0d295e7da +size 33554432 diff --git a/params_shard_133.bin b/params_shard_133.bin new file mode 100644 index 0000000000000000000000000000000000000000..ae29bea63265d2301046c4f7923d9dc3d9f818c8 --- /dev/null +++ b/params_shard_133.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8420e4805bf0b753a58c3f4cfc47be3ad834964bddfff36f51e2546832ef4f75 +size 117440512 diff --git a/params_shard_134.bin b/params_shard_134.bin new file mode 100644 index 0000000000000000000000000000000000000000..a865288aa7251aea1eab39dbdb86aacd510704d4 --- /dev/null +++ b/params_shard_134.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ae60701753b675fdbcbfbe6149e8a5688ec71c487423aad0b76f2c6c9b69cd +size 234881024 diff --git a/params_shard_135.bin b/params_shard_135.bin new file mode 100644 index 0000000000000000000000000000000000000000..395e0bc9d91edd7b01ea39a1a1957398a6945c83 --- /dev/null +++ b/params_shard_135.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58ef16ee7787388175be5077f3af960a7a48e63d61b6a025e5c72afe442f558b +size 41943040 diff --git a/params_shard_136.bin b/params_shard_136.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c30c09309b0a70666e0ed581b7e3844efcf42db --- /dev/null +++ b/params_shard_136.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:647e70ba64cb7b293030b9c8c04aea27646b83ac3fa990a68f2aabd21be9712e +size 33554432 diff --git a/params_shard_137.bin b/params_shard_137.bin new file mode 100644 index 0000000000000000000000000000000000000000..6cf9151213ac08bd9b194f652b19fbf77ce796b8 --- /dev/null +++ b/params_shard_137.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de6fbc71a37b76fccba7da4a3f30df2fbda66d3f37e48fc6f04f23d8cc7665df +size 234881024 diff --git a/params_shard_138.bin b/params_shard_138.bin new file mode 100644 index 0000000000000000000000000000000000000000..153027ab9cd37d17434e75056f46055c0f174df5 --- /dev/null +++ b/params_shard_138.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6ffc23d1109c323b9ed0a92494572e2afccb596667813315ff9398a9071b57 +size 29196288 diff --git a/params_shard_139.bin b/params_shard_139.bin new file mode 100644 index 0000000000000000000000000000000000000000..a177e12df77e1611c4144c651e474f21c7083199 --- /dev/null +++ b/params_shard_139.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3a9964872940f6fd49534c9cb95bc2d37ed58c3db3f746ed66bac6380a73389 +size 41943040 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..b718b3984a0186ef254ef88fead344374c97e590 --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:091126736db4827d3bcf9f7820992cf8df337788cdf565cd832f06e9f018bc31 +size 234881024 diff --git a/params_shard_140.bin b/params_shard_140.bin new file mode 100644 index 0000000000000000000000000000000000000000..14eab22f98f386be22aaa97570857c75349bd8c4 --- /dev/null +++ b/params_shard_140.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a166cd7c7d30fdf4a3da6424f71736c1b08e956e25c42720f9b6ffb59e9b6acb +size 33554432 diff --git a/params_shard_141.bin b/params_shard_141.bin new file mode 100644 index 0000000000000000000000000000000000000000..f987f1f724f1565e4f084a519815accc1bf7213c --- /dev/null +++ b/params_shard_141.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfbf52c20ee470bbe1f797edfa641b2b5723f2dd2f65e7158ce7b052d82d7b78 +size 117440512 diff --git a/params_shard_142.bin b/params_shard_142.bin new file mode 100644 index 0000000000000000000000000000000000000000..b2613629ade204d340cb43be8d2c46563a67756a --- /dev/null +++ b/params_shard_142.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9535b4035ffbf87139fd288eb9cfe18c7802359da712d3e42b566905a900030 +size 117440512 diff --git a/params_shard_143.bin b/params_shard_143.bin new file mode 100644 index 0000000000000000000000000000000000000000..d34fc20d6eb3e864c6e0836ae630c1ac257356fb --- /dev/null +++ b/params_shard_143.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3c95986d1219601e2350f7d5c8459657749a8b3e6eea56099a7bd9c62fa7f7 +size 234881024 diff --git a/params_shard_144.bin b/params_shard_144.bin new file mode 100644 index 0000000000000000000000000000000000000000..a01683c4ee571005c7f57fec32a86a5f765217ba --- /dev/null +++ b/params_shard_144.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e49d7bcdeb4051dea4415a59013e67d61ed3f1cbf382dd96bc08f3dd26554d2 +size 41943040 diff --git a/params_shard_145.bin b/params_shard_145.bin new file mode 100644 index 0000000000000000000000000000000000000000..e90042c9ed6ac0faf8cc5e3b24a401df51657e2c --- /dev/null +++ b/params_shard_145.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae9d00d3fdb20b23d88f0a09f91d27e6d80a0e508ca594cf6a6a036c562fb02 +size 33554432 diff --git a/params_shard_146.bin b/params_shard_146.bin new file mode 100644 index 0000000000000000000000000000000000000000..83c328ce1b1c96cd241ac0c9324910cf854e3298 --- /dev/null +++ b/params_shard_146.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ba4d2a6075ba7d416757e607558d539b3f3216e438226ea8602a47908b61dc +size 117440512 diff --git a/params_shard_147.bin b/params_shard_147.bin new file mode 100644 index 0000000000000000000000000000000000000000..46326779817464196ba73d71d4f643a4f9e2e966 --- /dev/null +++ b/params_shard_147.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a48048760fb7f6a339641cfc091c9982617d2605222d86f63c51e435c33af4b +size 234881024 diff --git a/params_shard_148.bin b/params_shard_148.bin new file mode 100644 index 0000000000000000000000000000000000000000..8534c5f68843e83b564de58484318cbc0bb4dc59 --- /dev/null +++ b/params_shard_148.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a0834b80100e25e43698c612e532f096fdd94cefdeb5fb3622cbaa58b654589 +size 30490624 diff --git a/params_shard_149.bin b/params_shard_149.bin new file mode 100644 index 0000000000000000000000000000000000000000..39844af19f5c1c0812a7ab4a6307065def129f14 --- /dev/null +++ b/params_shard_149.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a0159fc2cbd63ecf60291097c38360d406ae844969164be3324cc7bd3e248d +size 41943040 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..b89c34db7c0ae1fc28480377d87c27afb5dfe61a --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2445b4b8a964eb741bda84d2b33d6a2e20b813d76a0722b45ef472f7b0a140f0 +size 41943040 diff --git a/params_shard_150.bin b/params_shard_150.bin new file mode 100644 index 0000000000000000000000000000000000000000..5cab17d8277de91ce1b620971d14fa8c4fb176b2 --- /dev/null +++ b/params_shard_150.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f18b066e101a4f503acfd4fea82eb7a7e22009127a36f89bacdbcb476c31c6a7 +size 33554432 diff --git a/params_shard_151.bin b/params_shard_151.bin new file mode 100644 index 0000000000000000000000000000000000000000..6840b0ca493dc12938dd0910360f5c13f430697b --- /dev/null +++ b/params_shard_151.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f9a9f7e15a26e139db74c9bdf6b1f780d14cc8bc63d0e75e76c90c05fa18e6 +size 41943040 diff --git a/params_shard_152.bin b/params_shard_152.bin new file mode 100644 index 0000000000000000000000000000000000000000..c3247c76aa7b7a92f45888300609e5967e7286d6 --- /dev/null +++ b/params_shard_152.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d7db2796d01bc6316d6155bb719854a8ed2ed8b72c98fb31f61694f2239687c +size 33554432 diff --git a/params_shard_153.bin b/params_shard_153.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc1f84553abdca3b31d0edbf8d6c6ddb1da171ab --- /dev/null +++ b/params_shard_153.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119fe99a6f4213888e44f60fcefb6f5711cc8737d9dbc84dc9d2458cd70cf49f +size 117440512 diff --git a/params_shard_154.bin b/params_shard_154.bin new file mode 100644 index 0000000000000000000000000000000000000000..ecb0ae57ba1a32277646bd4b58e2fb4455a553e1 --- /dev/null +++ b/params_shard_154.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af17cc630f52db27fdcdf8c1bd9a0ea1ed0290f684eace90dee9d2f5a7ef9b37 +size 234881024 diff --git a/params_shard_155.bin b/params_shard_155.bin new file mode 100644 index 0000000000000000000000000000000000000000..70aa1a703d8e0011d3b486594c1af6a06b644cf3 --- /dev/null +++ b/params_shard_155.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b6b489137353c397481a3ea9ec8769de17c8845ad1ecbe7080815a28b79488 +size 117440512 diff --git a/params_shard_156.bin b/params_shard_156.bin new file mode 100644 index 0000000000000000000000000000000000000000..3403a9aa9d318a1343976a529858b625cc58cdca --- /dev/null +++ b/params_shard_156.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d053700d6d5fd701bd6187f8f7018d39ffe0181af7d1468cd1e5b14872eb16c0 +size 234881024 diff --git a/params_shard_157.bin b/params_shard_157.bin new file mode 100644 index 0000000000000000000000000000000000000000..65aa08c8aa7731a4ba2f62b99228d6a5d26524a9 --- /dev/null +++ b/params_shard_157.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5195fa71018a8a28a14df52cb66da9a6ebe3bbed0e41b3c27049e0dfd3cd6dee +size 26804224 diff --git a/params_shard_158.bin b/params_shard_158.bin new file mode 100644 index 0000000000000000000000000000000000000000..30ce847793fc1d226c7962978031a928ba75622a --- /dev/null +++ b/params_shard_158.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c39cd1aec90ed9c070199c3f7c1d8ea3effa84c00485d0fbda93e0b9a620fb78 +size 41943040 diff --git a/params_shard_159.bin b/params_shard_159.bin new file mode 100644 index 0000000000000000000000000000000000000000..f77c0685063dbc4b4409813c3e0526600edae6e1 --- /dev/null +++ b/params_shard_159.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aad8f92b9454d9c0386db1284fdedd6b36c3b04113495dba9ae4d6d22c57adf +size 33554432 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..c57e2fc360df68ac1bcd08269a48de926f62e095 --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d938e3ac78b2cf9227967cc7ee9bcdc1bad62cf50c9f696200155f38023b8480 +size 33554432 diff --git a/params_shard_160.bin b/params_shard_160.bin new file mode 100644 index 0000000000000000000000000000000000000000..a99491c163a4abf78760dacddc3fbb0f4a189948 --- /dev/null +++ b/params_shard_160.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b049f468817656bd8b25897db31a85acd7c7a6cb8f60f5b0b7e066b50597972c +size 117440512 diff --git a/params_shard_161.bin b/params_shard_161.bin new file mode 100644 index 0000000000000000000000000000000000000000..532982d44298a94a472574fc38491f8df98fff9d --- /dev/null +++ b/params_shard_161.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a92d4fcae6426ddaf9e844c87ae771a48dd39a163c1354f756cb1c98ceb4bd6 +size 234881024 diff --git a/params_shard_162.bin b/params_shard_162.bin new file mode 100644 index 0000000000000000000000000000000000000000..12f248ef3889caddde038c511448d0fe0fdf1eb2 --- /dev/null +++ b/params_shard_162.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be6e793cf8a60e0a78b65110e19822230d31bb3efd3fb9e91487e9544c06a66 +size 41943040 diff --git a/params_shard_163.bin b/params_shard_163.bin new file mode 100644 index 0000000000000000000000000000000000000000..89d95aa86b9406ee0ca99576344d3cfdb15ac1e3 --- /dev/null +++ b/params_shard_163.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bffc94275ed23b1ddef8c8abfd9663b9cbc1884f66634b8b0c062b3935e1bdd2 +size 33554432 diff --git a/params_shard_164.bin b/params_shard_164.bin new file mode 100644 index 0000000000000000000000000000000000000000..ca5f1d4fac4a3dd497a11a9bf384713993d84bcf --- /dev/null +++ b/params_shard_164.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d7003044851894222c728f85917d428156789fcae2c3c250264339c4c519ab +size 41943040 diff --git a/params_shard_165.bin b/params_shard_165.bin new file mode 100644 index 0000000000000000000000000000000000000000..d209c33b4d619f48d78ad91bf473f518dffc3a67 --- /dev/null +++ b/params_shard_165.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5b1a87cbc7bd7a90d1442cf179aaf1498716123d4721ce980fec9c11f180419 +size 117440512 diff --git a/params_shard_166.bin b/params_shard_166.bin new file mode 100644 index 0000000000000000000000000000000000000000..78d1e4572f6bc7d2cbd01c9237b06eb1c172a656 --- /dev/null +++ b/params_shard_166.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7932294d48770b7658b415a1fbe527770da1889e2d8eeda31ebdddacbe9de977 +size 234881024 diff --git a/params_shard_167.bin b/params_shard_167.bin new file mode 100644 index 0000000000000000000000000000000000000000..b544dd762518e94fde864f1ccd7a3d77b8dddfcd --- /dev/null +++ b/params_shard_167.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd231f13c3975ad6b860968f0efea7a4a344352e44163a2d3fbd2667237352a3 +size 28114944 diff --git a/params_shard_168.bin b/params_shard_168.bin new file mode 100644 index 0000000000000000000000000000000000000000..7eb318fda8645eead254bd32a2974d95a609f384 --- /dev/null +++ b/params_shard_168.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68bc1a97a2d345600a6551034f26ad88e46b19eca5b193c0bd46e1dd17319758 +size 117440512 diff --git a/params_shard_169.bin b/params_shard_169.bin new file mode 100644 index 0000000000000000000000000000000000000000..d905b9572fb5cb5f15857e468cd4612d5586bfa9 --- /dev/null +++ b/params_shard_169.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fde2e5fca99276ebb9dbf7d782b3379de64759bbee558e5a13c83ad359485b83 +size 234881024 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..8216d3a48ce2ea037046cb83fea6a760cf128737 --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc7a0fbd51f916061e108102d808c07035cc9a8098f818c80dfee608a5c90213 +size 117440512 diff --git a/params_shard_170.bin b/params_shard_170.bin new file mode 100644 index 0000000000000000000000000000000000000000..43336354580d14ee42c02e49486f3c8ec0a618e9 --- /dev/null +++ b/params_shard_170.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef9c15cdc7d81d4875e9cbcd2acf6d8438867490a7836393463edeae5773434 +size 41943040 diff --git a/params_shard_171.bin b/params_shard_171.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b0b34ba82cef06b18150faf9f2ee51d11c5dd64 --- /dev/null +++ b/params_shard_171.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fcbff339475a534b8d14fc2fb4db0c0a35d3ddac26d5f351eff97ccb83e8f51 +size 33554432 diff --git a/params_shard_172.bin b/params_shard_172.bin new file mode 100644 index 0000000000000000000000000000000000000000..c8710d9965d5cbf24d9963b440d23ad33124cf8b --- /dev/null +++ b/params_shard_172.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd63d53710f63008f73eb1ce7a0fd91bfe3ea733a31d16418ca6f17cf4ba12c +size 117440512 diff --git a/params_shard_173.bin b/params_shard_173.bin new file mode 100644 index 0000000000000000000000000000000000000000..5ade3aa97fe4e6982757a782815bbb774c0990bd --- /dev/null +++ b/params_shard_173.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed050a20a7e714271c85e026e2c64e31e58b0947b18e4168f95003a4e8d701bc +size 234881024 diff --git a/params_shard_174.bin b/params_shard_174.bin new file mode 100644 index 0000000000000000000000000000000000000000..6138c9bb554809b5c0f2c41a796472a80ce0ae1b --- /dev/null +++ b/params_shard_174.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed7322613a414ee34854398cbf91950a6e7e88fabca756e5df7e7b38e28bf151 +size 41943040 diff --git a/params_shard_175.bin b/params_shard_175.bin new file mode 100644 index 0000000000000000000000000000000000000000..18d022f3c8dcea360f21ff8f0711b1af352698be --- /dev/null +++ b/params_shard_175.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e704898dceda756807c34d92d9af2743946f9572ded127164b0fcea05f929af +size 33554432 diff --git a/params_shard_176.bin b/params_shard_176.bin new file mode 100644 index 0000000000000000000000000000000000000000..c926aef1d6e624da233e3a1f615dd0bbc8b76a4d --- /dev/null +++ b/params_shard_176.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c4bd5026989dd2678b9b52f954036fde2f5931a7cfafe0b5739b24111c04d1 +size 33112064 diff --git a/params_shard_177.bin b/params_shard_177.bin new file mode 100644 index 0000000000000000000000000000000000000000..07256cdbac8dde235100b9cdecc2e5adf1f97b35 --- /dev/null +++ b/params_shard_177.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:464b0ea430e9645c14beef71d26773b67c4a2a1100379a41ea53f465ab5238f7 +size 41943040 diff --git a/params_shard_178.bin b/params_shard_178.bin new file mode 100644 index 0000000000000000000000000000000000000000..22169d3e31dd41b7434290aeac83ed1ba277fbb1 --- /dev/null +++ b/params_shard_178.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc8a3b6f8b423c9c00461e1d36f9e2f261493983b9ce54901fc2052b8959913c +size 117440512 diff --git a/params_shard_179.bin b/params_shard_179.bin new file mode 100644 index 0000000000000000000000000000000000000000..1b37600a24f2f47c6dbd0955883a261ad5ec7206 --- /dev/null +++ b/params_shard_179.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d87aa624c7eadc3c2fb926aa1c117637db9095b2d167b4ef8fe0bb4f7119b88 +size 234881024 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..acbc2bf086066a58dee0f8cf1ac5bfa187563f14 --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13ef8d343db8922a295378d0a2da205ded31ecc6332c22aeba71fc12bb804676 +size 117440512 diff --git a/params_shard_180.bin b/params_shard_180.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ddc3474f99bbf9342c4e2b3b2f8c012c2cb98e2 --- /dev/null +++ b/params_shard_180.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd9928805f5435182d0c6a1e5ce2460fcee3e5280f1388064e602e5a14e35060 +size 33554432 diff --git a/params_shard_181.bin b/params_shard_181.bin new file mode 100644 index 0000000000000000000000000000000000000000..49e6149b02b2a17055b01b604b4e6234572d47ac --- /dev/null +++ b/params_shard_181.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c2c84abdc6966218bd5363bd95fbbefe36fb4c399a89ff0e21087bf03b1786d +size 117440512 diff --git a/params_shard_182.bin b/params_shard_182.bin new file mode 100644 index 0000000000000000000000000000000000000000..09dca7cabd3da0ef16cd2f197926bb342c03c21b --- /dev/null +++ b/params_shard_182.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a0e2510704a3050ca88c5de51d3d30f9097a28d928699a7468268bc2779f82 +size 234881024 diff --git a/params_shard_183.bin b/params_shard_183.bin new file mode 100644 index 0000000000000000000000000000000000000000..3b22f81bcfb1b1a2cf52185213f45be9f04495b2 --- /dev/null +++ b/params_shard_183.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f47e4188c3aa6dc56459cc80ac8bacf719d7d8beda5a7fc0f759164bad58d939 +size 41943040 diff --git a/params_shard_184.bin b/params_shard_184.bin new file mode 100644 index 0000000000000000000000000000000000000000..65c258a268e88c5db0c308026b52d5f0cc82a42f --- /dev/null +++ b/params_shard_184.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c57f5ee362756cf21f3104aa926229c5d46948218b89d7b96c0c596bbe54315e +size 33554432 diff --git a/params_shard_185.bin b/params_shard_185.bin new file mode 100644 index 0000000000000000000000000000000000000000..4d10af45f2e4ba4765ac0913ff7b3b1452ebfa0a --- /dev/null +++ b/params_shard_185.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9397d29f558c176b8cc6608db5bf3df15857b783774edcbbd12b7416188584c +size 117440512 diff --git a/params_shard_186.bin b/params_shard_186.bin new file mode 100644 index 0000000000000000000000000000000000000000..bdd31f2ce5675803fe7a7faaf3cbdafca57097a0 --- /dev/null +++ b/params_shard_186.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2302ee48124193e6df66dbfe24bbbafa08165b37dbce865f74ea3911d1641e88 +size 234881024 diff --git a/params_shard_187.bin b/params_shard_187.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f463817c49396b71a8ddbe02356670e71c02a6a --- /dev/null +++ b/params_shard_187.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbb42b05150eb87e117c61bbab58c55758971779102042ca945d297404a8ae25 +size 31522816 diff --git a/params_shard_188.bin b/params_shard_188.bin new file mode 100644 index 0000000000000000000000000000000000000000..aa79623211322a24b06ea2ec76be27a095529b54 --- /dev/null +++ b/params_shard_188.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27fb53c5d70efade4d77e2c8042a7dd448232346ab815d434d5eaca109b04fb5 +size 41943040 diff --git a/params_shard_189.bin b/params_shard_189.bin new file mode 100644 index 0000000000000000000000000000000000000000..4725c694aa7aba4d0cdcefae1e6811c9e51167f3 --- /dev/null +++ b/params_shard_189.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a821c93a4135eec7366e6b8f73821f7634a4543fd28a5d38a16fc3a852af0029 +size 33554432 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..86c45694437dd3521ef68d89cb09c4957f78b832 --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:540d86bab0c90dc352e1c36b13e06d52a0e0b7599d3e3fd246eb35d087f8ef4f +size 234881024 diff --git a/params_shard_190.bin b/params_shard_190.bin new file mode 100644 index 0000000000000000000000000000000000000000..bbd58b2b1dbd51ff96b1ee66a802b737d2a5f096 --- /dev/null +++ b/params_shard_190.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd792a40c41b741581fbd44fea89352cdb362cd2b5151a2ff6b2dd0ff02871e +size 117440512 diff --git a/params_shard_191.bin b/params_shard_191.bin new file mode 100644 index 0000000000000000000000000000000000000000..d7a734261548ae35afd35c5d98546f772d096d98 --- /dev/null +++ b/params_shard_191.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ba0f2a8a3e5ccf9c4c67c38ad34023f780a3061f231552c49ce275e5f11708 +size 234881024 diff --git a/params_shard_192.bin b/params_shard_192.bin new file mode 100644 index 0000000000000000000000000000000000000000..c57e9b8f06b91430b6685a2d60a7ed38ec657200 --- /dev/null +++ b/params_shard_192.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc9d70661c8fb99c2d3400dac2bd9ddda980658753a8e0f9ac8d1646b6ff7ce +size 41943040 diff --git a/params_shard_193.bin b/params_shard_193.bin new file mode 100644 index 0000000000000000000000000000000000000000..58efa0ede7dccd75496e8ca3d04e6f6139228226 --- /dev/null +++ b/params_shard_193.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9040abfc98b604764f7d4e91fdf21dca76322d9701b4e1c76a86ba63354326ee +size 33554432 diff --git a/params_shard_194.bin b/params_shard_194.bin new file mode 100644 index 0000000000000000000000000000000000000000..c28ae5dbd5ded2fccb879939efdae4000742fefc --- /dev/null +++ b/params_shard_194.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9ab0ed39a798c0ee8cb531ff43c0bab9f271a0fdc045cffe651283d99b01e51 +size 117440512 diff --git a/params_shard_195.bin b/params_shard_195.bin new file mode 100644 index 0000000000000000000000000000000000000000..093c05c59bc535b40662ce54b10b5f4a89bb790b --- /dev/null +++ b/params_shard_195.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f95b7e79bc965177681fba5199232141e0c8c7a2e8f44d60b0fdf0d68696239 +size 234881024 diff --git a/params_shard_196.bin b/params_shard_196.bin new file mode 100644 index 0000000000000000000000000000000000000000..498817e3be8f0ffd05c574ba652d5134d1493661 --- /dev/null +++ b/params_shard_196.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8fb0bbe6ab15cc9eb63607c0103aebedf5ee8d7d8792c20c85b50e568fff5bf +size 26820608 diff --git a/params_shard_197.bin b/params_shard_197.bin new file mode 100644 index 0000000000000000000000000000000000000000..c22c0013744b3e96184e146bc188d2c30f65f3a4 --- /dev/null +++ b/params_shard_197.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4f7482e77bc98a7ae1bbfd46b359d208423e14d4d05ab8751350dcf29a87f1d +size 41943040 diff --git a/params_shard_198.bin b/params_shard_198.bin new file mode 100644 index 0000000000000000000000000000000000000000..bc3aa2cdc1574d2d75230aff2bbc77c4c7d69814 --- /dev/null +++ b/params_shard_198.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9d4ecea7a3fdf33b54d2430211b5aaff0f77576477665e450e70dd06f235a20 +size 33554432 diff --git a/params_shard_199.bin b/params_shard_199.bin new file mode 100644 index 0000000000000000000000000000000000000000..f85f76ea82c47225cadcc25831fd4b2d3063613d --- /dev/null +++ b/params_shard_199.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3181b9c1744328d0f6b42ff515f8daa1cedfa2939af2365ba249c2476c720604 +size 234881024 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..7679d5be841ace25d48445f385b0a3c2e57fe313 --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a619c16ab00737dcc7c5bb973ecf9eca3adae47bfa7fcd91ffb77aaf97166557 +size 234881024 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ef4efc2521bfbef4a19a9a9f79ea7c9b5e39aa3 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10c4d5fdf8c6eadc8af4fd086302bde1f57dc4c1ccc679ea967413d39634f23f +size 26804224 diff --git a/params_shard_200.bin b/params_shard_200.bin new file mode 100644 index 0000000000000000000000000000000000000000..ce87238ba395993692145d33f3b9ba592dfbb380 --- /dev/null +++ b/params_shard_200.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a1c488169718635b3140e9d277fc21365153f8effb67711c9136be6bef80584 +size 41943040 diff --git a/params_shard_201.bin b/params_shard_201.bin new file mode 100644 index 0000000000000000000000000000000000000000..762dde4ccf8541d52e7924d871903ea58764ce43 --- /dev/null +++ b/params_shard_201.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e49862d8b990b74bdbe66df1c33f64f309b685635242e01b1550c1da72d568b +size 33554432 diff --git a/params_shard_202.bin b/params_shard_202.bin new file mode 100644 index 0000000000000000000000000000000000000000..b386f29d7e5bd4c66e62280f09f4fe5cae41d58a --- /dev/null +++ b/params_shard_202.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5020ee7ec0b87bfef630b6921a29d5204ee3bf3dcd03a86aa3d7f23753276e6a +size 117440512 diff --git a/params_shard_203.bin b/params_shard_203.bin new file mode 100644 index 0000000000000000000000000000000000000000..7d82727bc62174d56a377bfabcd6f83be0d81015 --- /dev/null +++ b/params_shard_203.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:636ad9066e7063fa3d65af6facda7921e179acaa73fbd91286257d82f7c2883d +size 117440512 diff --git a/params_shard_204.bin b/params_shard_204.bin new file mode 100644 index 0000000000000000000000000000000000000000..6a19410090fa8cb4c8282ec332f2dc40b38b43d2 --- /dev/null +++ b/params_shard_204.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56288f2e0139f617ba1b101a95336ea8f9c995859333378504f437d18f1fae1a +size 234881024 diff --git a/params_shard_205.bin b/params_shard_205.bin new file mode 100644 index 0000000000000000000000000000000000000000..64fa8d613d5d593cacea61cce168b9178b90913e --- /dev/null +++ b/params_shard_205.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c0f1b3801bd4841b94496a09abce693225f8f12b57a02aa3f43bc46f410e8c +size 26804224 diff --git a/params_shard_206.bin b/params_shard_206.bin new file mode 100644 index 0000000000000000000000000000000000000000..aeeb8cd59d5143977743e6a526a30df2e65b3111 --- /dev/null +++ b/params_shard_206.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aaa64ac3757733134b4fff1d66df184af34abe138c455f97b589613090d5ebd +size 41943040 diff --git a/params_shard_207.bin b/params_shard_207.bin new file mode 100644 index 0000000000000000000000000000000000000000..ec2e237e5a39880dd2b3e5a6fb52238cd1f614d7 --- /dev/null +++ b/params_shard_207.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:724e94db589601e3b552c033388e53f559c4713101f9e72e60d4d8fd45d9d254 +size 33554432 diff --git a/params_shard_208.bin b/params_shard_208.bin new file mode 100644 index 0000000000000000000000000000000000000000..e8f4255d57b57ea1120974866642d5694a2468f6 --- /dev/null +++ b/params_shard_208.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8403fd8cb28006585401816567718bdc0c8e36b7903bba98ddf55a35098ac45 +size 117440512 diff --git a/params_shard_209.bin b/params_shard_209.bin new file mode 100644 index 0000000000000000000000000000000000000000..c36a014f80f615a09a6bdd3dfcc4a65f6e8ec380 --- /dev/null +++ b/params_shard_209.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d18db84b06c0d0f1021ee62215ec55c6338c6e3c5ef60b860e46b55d4445bd5 +size 234881024 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..e5344f30cf568d5dbd8aac2e8ce2345bfb9cd704 --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2095b62d3304d73f6bf4215112a843e6da94061363f4fa5e4488fa96b0825446 +size 41943040 diff --git a/params_shard_210.bin b/params_shard_210.bin new file mode 100644 index 0000000000000000000000000000000000000000..85623f21985ba9f26ca89513f3460eb1d4de0bbf --- /dev/null +++ b/params_shard_210.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee8f949316de84077b9373d6716eed410be48c480251eca6bb2f85f9976a1ffe +size 41943040 diff --git a/params_shard_211.bin b/params_shard_211.bin new file mode 100644 index 0000000000000000000000000000000000000000..2865efc38683995f2e9b1163b86718132e6ac077 --- /dev/null +++ b/params_shard_211.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60a838e0941536de503a49d0965c7a6f031f0c9a5b2bcc6ba1ba2f65ada321d +size 33554432 diff --git a/params_shard_212.bin b/params_shard_212.bin new file mode 100644 index 0000000000000000000000000000000000000000..a2e8c1beaa34954abf657d10a1c9ec800f696fed --- /dev/null +++ b/params_shard_212.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633654157accfaf7c1c79c8cb39b41b1231a18731031258ea176ba0059f98b9e +size 41943040 diff --git a/params_shard_213.bin b/params_shard_213.bin new file mode 100644 index 0000000000000000000000000000000000000000..c815eaa25a0d359f61b26bcad095b796870013e4 --- /dev/null +++ b/params_shard_213.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84fbf6750a0a394d7fdcd648e58471abdb4a75b4c137815e6f18b7ea476039e4 +size 33554432 diff --git a/params_shard_214.bin b/params_shard_214.bin new file mode 100644 index 0000000000000000000000000000000000000000..2339ec370e0e7dee8d4fef0c470eed78f001e8a7 --- /dev/null +++ b/params_shard_214.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20356d687c5d12b6a3753a64b5d242d4501dc33475e4ca95e1054c61d6800e93 +size 117440512 diff --git a/params_shard_215.bin b/params_shard_215.bin new file mode 100644 index 0000000000000000000000000000000000000000..ffaa9932f05a16c2fa614e66482db0a04107d147 --- /dev/null +++ b/params_shard_215.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9dd2a2dbed12946db4677adf028820f0dbc6879f6292976a285672e90ba08fb +size 234881024 diff --git a/params_shard_216.bin b/params_shard_216.bin new file mode 100644 index 0000000000000000000000000000000000000000..805303f96dbdbef2c63e6142b6fdb38a6ed22eb0 --- /dev/null +++ b/params_shard_216.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f672a4eaba54d1301b34b5536ff78b5e42a6f07a8f630827f6084ac8327e46c4 +size 29163520 diff --git a/params_shard_217.bin b/params_shard_217.bin new file mode 100644 index 0000000000000000000000000000000000000000..147b6e63ccbe8903eac12efabedcd5eaa7f103a8 --- /dev/null +++ b/params_shard_217.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5be1a804b20048bb98a0cafc80e6de9700d7820266db5b0dec8f84bee1275ba +size 117440512 diff --git a/params_shard_218.bin b/params_shard_218.bin new file mode 100644 index 0000000000000000000000000000000000000000..cea1d636a2fe2ad517a2c7e98832523e9a1a3ccc --- /dev/null +++ b/params_shard_218.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd3069afb4af1f712eb5fb568768311f5126cc63bb4794444abded57158e5dbc +size 234881024 diff --git a/params_shard_219.bin b/params_shard_219.bin new file mode 100644 index 0000000000000000000000000000000000000000..3411f513627979c34b83b1475bd9b3ad805a5194 --- /dev/null +++ b/params_shard_219.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349a263d7ff4ef1ef0788364cc6e482ea8bb6a80be119633e093985f89206d88 +size 41943040 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..606d00031e3834ba2d7d0d7204cb09884eb2604b --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd793de5beac2a5b9d840315dbc5e6405cba28ea53391e9f7079d63a3545077 +size 33554432 diff --git a/params_shard_220.bin b/params_shard_220.bin new file mode 100644 index 0000000000000000000000000000000000000000..6602559ac893706b6db412bdf3efdf28b499ad92 --- /dev/null +++ b/params_shard_220.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab8bed832ba4ccfa0a96fbc8cbb16f43b962eef33c5a8f157577e6b372bece01 +size 33554432 diff --git a/params_shard_221.bin b/params_shard_221.bin new file mode 100644 index 0000000000000000000000000000000000000000..ab943a7132c1ed046403aacf9f145bb8d532da0c --- /dev/null +++ b/params_shard_221.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fd97e1707660475c3b3b8cf3e724da0b9bd63541ce34ea64960e711ea5f7864 +size 117440512 diff --git a/params_shard_222.bin b/params_shard_222.bin new file mode 100644 index 0000000000000000000000000000000000000000..257483ff067ac4d514361e2f81e73181e5dd344e --- /dev/null +++ b/params_shard_222.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1287d5b08ccc4db875d1be04b2fe70e68a9fb9144a71186f504c36373e47a3e5 +size 234881024 diff --git a/params_shard_223.bin b/params_shard_223.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b93283bcbf4975549ec4ac05c6ecfa853983cbe --- /dev/null +++ b/params_shard_223.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62cb3bbba7e6c94a087bbbfab5b4587c314a933181120b33f84f282f29d9ecee +size 41943040 diff --git a/params_shard_224.bin b/params_shard_224.bin new file mode 100644 index 0000000000000000000000000000000000000000..79258772931fdc8ced55645ee69d06574d336f22 --- /dev/null +++ b/params_shard_224.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc837994dbdf4a7ea3b9ec4b74570a9f36ecc4a7d7b427ef792b9fc8086b3ccf +size 33554432 diff --git a/params_shard_225.bin b/params_shard_225.bin new file mode 100644 index 0000000000000000000000000000000000000000..a6f625a3f4150af29bb8e237dde74d65756b6e48 --- /dev/null +++ b/params_shard_225.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18a8bf279681664b1cf2f704c6dc41317b04738b111158b906394224c2a957d8 +size 33112064 diff --git a/params_shard_226.bin b/params_shard_226.bin new file mode 100644 index 0000000000000000000000000000000000000000..b14e7bb0c55e13674fe1fff1b99d060a3db94ccc --- /dev/null +++ b/params_shard_226.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4df5ef68b08e55492b4ad9bc79d0fe627219b2e35e8bc8f14033af86c3a6cb5 +size 41943040 diff --git a/params_shard_227.bin b/params_shard_227.bin new file mode 100644 index 0000000000000000000000000000000000000000..8db6201ff6bc1cc642312bfb0d794c9ee86ad74c --- /dev/null +++ b/params_shard_227.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c64a8b34b80e873154cd45c2682296e0048c64fdbb0cd973702950ab30f1cc34 +size 117440512 diff --git a/params_shard_228.bin b/params_shard_228.bin new file mode 100644 index 0000000000000000000000000000000000000000..89251cd2d7431c664b8a37c070a08ce27ffb2015 --- /dev/null +++ b/params_shard_228.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5f435824d2309e04508e55d39b44c6fa7ae539dd1b05f387b96e488a654da15 +size 234881024 diff --git a/params_shard_229.bin b/params_shard_229.bin new file mode 100644 index 0000000000000000000000000000000000000000..4ffc4d5edfbf763e53febb98f18e9a26eae73fc1 --- /dev/null +++ b/params_shard_229.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d99e3f72710e657a87bce3735858c42b42a88e2aa76344742fd5f8de1a37816 +size 33554432 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..3de65e19a94faca665e8e1c72137643034f9bca6 --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555537ccaa432aa08cebd50fc314e5b24ddd3d42667b8e63ff8f6ef0ed893514 +size 117440512 diff --git a/params_shard_230.bin b/params_shard_230.bin new file mode 100644 index 0000000000000000000000000000000000000000..1917ecedb0b3267558c04a70c8db26024ea6233c --- /dev/null +++ b/params_shard_230.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:479cefe4c34166f562988209171aba4bc945468417c13c35123bb55611053e33 +size 117440512 diff --git a/params_shard_231.bin b/params_shard_231.bin new file mode 100644 index 0000000000000000000000000000000000000000..3331e63e460b2377048459b4d98f8de59bf2d320 --- /dev/null +++ b/params_shard_231.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b81435a909e205dbc1dee57842b1b1cb597e9bce7c0ecd85c438a5f779a4c1f +size 234881024 diff --git a/params_shard_232.bin b/params_shard_232.bin new file mode 100644 index 0000000000000000000000000000000000000000..e0db4f118cf371d7997d13f68294650c53ed5743 --- /dev/null +++ b/params_shard_232.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd79c8470558d7f6a133c06fd95d58f69f48ee9023b8ed29e5f9d5ccf48984b +size 41943040 diff --git a/params_shard_233.bin b/params_shard_233.bin new file mode 100644 index 0000000000000000000000000000000000000000..de32386bb93360ad903f3c92913d7a52819e4d3e --- /dev/null +++ b/params_shard_233.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb7e09a876c1fecd17b37d56d1fcb6853b0f40904694f91f4cc41bc91be3b5f2 +size 33554432 diff --git a/params_shard_234.bin b/params_shard_234.bin new file mode 100644 index 0000000000000000000000000000000000000000..040dbacfea0ba7803d555c05c299faca02c8f12e --- /dev/null +++ b/params_shard_234.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a18494fcb06b0b987cc46ee40cf20aa950e0faf4509d0e0630844596400246 +size 117440512 diff --git a/params_shard_235.bin b/params_shard_235.bin new file mode 100644 index 0000000000000000000000000000000000000000..2b3947ee9f66c5d91cabf23e28e9b304dedc447d --- /dev/null +++ b/params_shard_235.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23319b643e19c848074fd10e78dccd0f0cabd8f700230c9d91bf1b566e04bbd8 +size 234881024 diff --git a/params_shard_236.bin b/params_shard_236.bin new file mode 100644 index 0000000000000000000000000000000000000000..f70ed820fa68385f09ce9cb91edf61d43d449bac --- /dev/null +++ b/params_shard_236.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:726cb916e89e9c167fa5ee31837d69ea7972c61384f2b13caf9f4f4cecffac22 +size 31522816 diff --git a/params_shard_237.bin b/params_shard_237.bin new file mode 100644 index 0000000000000000000000000000000000000000..e83c19b1b25e8e2af9fd72a882e068d897d0a610 --- /dev/null +++ b/params_shard_237.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8320807fec2a1edae58f34af69849a12ec003125264821aa63f4fafbe6015b54 +size 41943040 diff --git a/params_shard_238.bin b/params_shard_238.bin new file mode 100644 index 0000000000000000000000000000000000000000..559e5b7032bd4b5ef698e5a7c83676e687c8435d --- /dev/null +++ b/params_shard_238.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3155f3dcd387d7efdc4f1605e9da87039e0f40cdfa10134f263459a154d1de7 +size 33554432 diff --git a/params_shard_239.bin b/params_shard_239.bin new file mode 100644 index 0000000000000000000000000000000000000000..3c39a2f121b226e2622555df675787efd2b19709 --- /dev/null +++ b/params_shard_239.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:144fdacac402e5b309a9c05387442572095cb4917b5f8aabc4139cd7ebdbef89 +size 117440512 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..7aed55e82f94a547212bdb18f6f49d0a4e222d5e --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fd692ae841dca29d3a2f592286ae79c18bef6995c238b9d16070bb342ad6624 +size 234881024 diff --git a/params_shard_240.bin b/params_shard_240.bin new file mode 100644 index 0000000000000000000000000000000000000000..8a1390f6ab7e7390396c41960de7776b682b61b7 --- /dev/null +++ b/params_shard_240.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccacd63531f65911b0c02de63a5d4a3c38bf189680b91a21ae7b86a5c6098bb7 +size 234881024 diff --git a/params_shard_241.bin b/params_shard_241.bin new file mode 100644 index 0000000000000000000000000000000000000000..e0a890f446697017d12e696d984bd6ff7f95600a --- /dev/null +++ b/params_shard_241.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6f1183645f20d7e8bee7e4f17ae59425bcfeb896c30639df071cfd268c2a30 +size 41943040 diff --git a/params_shard_242.bin b/params_shard_242.bin new file mode 100644 index 0000000000000000000000000000000000000000..ed9750f397bc8349af9d44bfee89c8afca4f2503 --- /dev/null +++ b/params_shard_242.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0e93566a128acdf3687003e1c49629d053cd2d96e819a4d6aa3e2f0150cff62 +size 33554432 diff --git a/params_shard_243.bin b/params_shard_243.bin new file mode 100644 index 0000000000000000000000000000000000000000..3d89c988afdb8735eb7e6f95936a718407905e32 --- /dev/null +++ b/params_shard_243.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c35d732603654954a816cd772b0bb833c75449ce72c89126a20500475f09b3d +size 117440512 diff --git a/params_shard_244.bin b/params_shard_244.bin new file mode 100644 index 0000000000000000000000000000000000000000..ed3f1da1caddf340f33a58ed5d86ef4d89f50e8a --- /dev/null +++ b/params_shard_244.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3835ce84da53bbd2aa69d1c2c1f83442f60bd3ec27ba19e9ae3f31699929acb0 +size 234881024 diff --git a/params_shard_245.bin b/params_shard_245.bin new file mode 100644 index 0000000000000000000000000000000000000000..247c5c0b6dabf2cd8d6154f1b9c688e237f22a20 --- /dev/null +++ b/params_shard_245.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ee2c51e94075b93b93d638bd384cde5f83f564ece449559716f1325cdb7b75e +size 26820608 diff --git a/params_shard_246.bin b/params_shard_246.bin new file mode 100644 index 0000000000000000000000000000000000000000..a09f50b13091e19c6791bc8225c392b8157e27a8 --- /dev/null +++ b/params_shard_246.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80eb862da4104aa834618eb5403a8a79530890f0703a5af2bc85c75c11dade36 +size 41943040 diff --git a/params_shard_247.bin b/params_shard_247.bin new file mode 100644 index 0000000000000000000000000000000000000000..798cbd60893b5caaef058cbc013fe77f724b5d3b --- /dev/null +++ b/params_shard_247.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3c7c34186ca41f32e82d83d455e76126d01bd7fb8586eb9a5fe4bb8732dd2ff +size 33554432 diff --git a/params_shard_248.bin b/params_shard_248.bin new file mode 100644 index 0000000000000000000000000000000000000000..10fece99465f0c1cfdd13710fa5dd82c98c1b6d7 --- /dev/null +++ b/params_shard_248.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2ee4030d0c0693bc979ddd85296b1969208e78924750ecfcdffca756b2a0967 +size 234881024 diff --git a/params_shard_249.bin b/params_shard_249.bin new file mode 100644 index 0000000000000000000000000000000000000000..6235f16d40b317aec02049114ad6b6c7f507ff31 --- /dev/null +++ b/params_shard_249.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0891053473efa6a2e2c603a859a2e326d7f1334579d3fa7ddf7c82c1f3ebf87e +size 41943040 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..6141cc03433db09f63a70bf7702c80023e47a5de --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbcdc527cb7f933936ba93bbc76356683bd17353dc8e0611dbe41a3aeeb82921 +size 41943040 diff --git a/params_shard_250.bin b/params_shard_250.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f44015f8bcf7637815d85992cc78bf0353bad4c --- /dev/null +++ b/params_shard_250.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d731c265b1f1563960dd8e908ffc1b58ba288fd999ede09585fef256123e6529 +size 33554432 diff --git a/params_shard_251.bin b/params_shard_251.bin new file mode 100644 index 0000000000000000000000000000000000000000..46089857ef33f07ae7bc0ed4cc8a8d7c8951b412 --- /dev/null +++ b/params_shard_251.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c44c2f0996021d793c740e7c6e37bcdac338157995d9eded4f7d9700935360 +size 117440512 diff --git a/params_shard_252.bin b/params_shard_252.bin new file mode 100644 index 0000000000000000000000000000000000000000..d31c7ef6724f183d9750154375476b0fa041bae5 --- /dev/null +++ b/params_shard_252.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3792a80f9d701d13b6b97c7d5562579a074394eb25eb429ebeea9d9f5d43cbe3 +size 117440512 diff --git a/params_shard_253.bin b/params_shard_253.bin new file mode 100644 index 0000000000000000000000000000000000000000..acee2b051ff79f33dc67dcf1cb8b47d970546a9c --- /dev/null +++ b/params_shard_253.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:363c4ce00e8fe5ac82fccdf8a4cbc83e68f53bd0d5a7260676c18b7c5d5ed81c +size 234881024 diff --git a/params_shard_254.bin b/params_shard_254.bin new file mode 100644 index 0000000000000000000000000000000000000000..912fb4314aab6c66c3b5aaa2bcc1c350f7054270 --- /dev/null +++ b/params_shard_254.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f39adb2d6d09593345f190f93094144a68ba9399e042e908b023815b402ae1a +size 26804224 diff --git a/params_shard_255.bin b/params_shard_255.bin new file mode 100644 index 0000000000000000000000000000000000000000..4b10953b3c4b9019646c1e311133d099c0fc8c34 --- /dev/null +++ b/params_shard_255.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6540ccd487ecacedef73a5c8f0d7923bc083af2165b5e8c45560a7d40ff01207 +size 41943040 diff --git a/params_shard_256.bin b/params_shard_256.bin new file mode 100644 index 0000000000000000000000000000000000000000..7267e42c85f961960cfbfe71c291e6546aaccd29 --- /dev/null +++ b/params_shard_256.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b989f26fd9ebf92a553a1de599b26520045575e61ccbec7d570061e2bfd4db4a +size 33554432 diff --git a/params_shard_257.bin b/params_shard_257.bin new file mode 100644 index 0000000000000000000000000000000000000000..72dc10aaa123438a9051d5618d05d5d44b480450 --- /dev/null +++ b/params_shard_257.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2f10e26ec63222f6fe9c6bdc1e18624c1af9e6a79c92a533df02a6566e6e01 +size 117440512 diff --git a/params_shard_258.bin b/params_shard_258.bin new file mode 100644 index 0000000000000000000000000000000000000000..e59b753e83a5c85edac0e519bee2dc9e0ad4abc6 --- /dev/null +++ b/params_shard_258.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f72682f8ed1daa53a5df85d08a121870879fd091c3920f46f53467af6996fc0f +size 234881024 diff --git a/params_shard_259.bin b/params_shard_259.bin new file mode 100644 index 0000000000000000000000000000000000000000..faa035af4ad2dc1e921345e468ba4e845ae5f31f --- /dev/null +++ b/params_shard_259.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b4c021a6e6aa6d1f739e5a7be29c7f30c7682d3a39ab0ad5e96f7885f0081c7 +size 41943040 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..80ad0605aae257da1c3cd29f89947e8f05d8fe01 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87ec60d4c766621bff60cc373d1065273c603c9eb39ba4ea2befffcae5f27b76 +size 33554432 diff --git a/params_shard_260.bin b/params_shard_260.bin new file mode 100644 index 0000000000000000000000000000000000000000..9406e1b30f6a37eb210758322f3c3b0710cc0b1f --- /dev/null +++ b/params_shard_260.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed5ac64c46c485f7eb594bd6d2852d62836eadd0759df3327999258c8957138c +size 33554432 diff --git a/params_shard_261.bin b/params_shard_261.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d1242e9cf5c38188a468e2ec69d58e9db092383 --- /dev/null +++ b/params_shard_261.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0bb8e0ad61481c5cc405807ad6f1c3a6196e1185e16fa1bd49e96f719e34953 +size 41943040 diff --git a/params_shard_262.bin b/params_shard_262.bin new file mode 100644 index 0000000000000000000000000000000000000000..b93c0c38d551b52c45aa58298be5f17aba0898cb --- /dev/null +++ b/params_shard_262.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d82393597a6b7e3e9260deabc784361c987292e9d97cf57dd736dcad93f6a2 +size 33554432 diff --git a/params_shard_263.bin b/params_shard_263.bin new file mode 100644 index 0000000000000000000000000000000000000000..57b094467e65c3cdedb56cbe6447f6395221d831 --- /dev/null +++ b/params_shard_263.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f816afc25d617ef37b24365763456bd717b6a8a143521040ae0862dfadb52194 +size 117440512 diff --git a/params_shard_264.bin b/params_shard_264.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1f6454683099b93a80cbd0f467f5566994fa64e --- /dev/null +++ b/params_shard_264.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7057199d2ed17fd70e59879a7061a3b8adafdb8ecd295ecb728bdf4fcb97c4b +size 234881024 diff --git a/params_shard_265.bin b/params_shard_265.bin new file mode 100644 index 0000000000000000000000000000000000000000..46b42156360e713b5fdae02d10770a0ece484e81 --- /dev/null +++ b/params_shard_265.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3c2789ad467215f42d6edcc2da671124c41b3d94d9339a46cb3670ae88eed3 +size 29163520 diff --git a/params_shard_266.bin b/params_shard_266.bin new file mode 100644 index 0000000000000000000000000000000000000000..440ef061ca08f8f8bde94d90f72a95d83a0303bc --- /dev/null +++ b/params_shard_266.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d0fea00f04a8f7d90ff1cf97572431db38f44d66522142294986889f4f88d34 +size 117440512 diff --git a/params_shard_267.bin b/params_shard_267.bin new file mode 100644 index 0000000000000000000000000000000000000000..d453b1839cd518a0fa86a507e2384a3f124628d8 --- /dev/null +++ b/params_shard_267.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0a928889130af912b53b3ad06e7ec21a149f3f5606234011eb8b1bc8102397f +size 234881024 diff --git a/params_shard_268.bin b/params_shard_268.bin new file mode 100644 index 0000000000000000000000000000000000000000..bacb940b26327c9c8dc920550b4ff00ce5712b5b --- /dev/null +++ b/params_shard_268.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff2fe4732acf767f473e474fec86f0d8d16cbad163f3786b95fb63e9e6f963d4 +size 41943040 diff --git a/params_shard_269.bin b/params_shard_269.bin new file mode 100644 index 0000000000000000000000000000000000000000..99e4128e0db014f9cbacfcec7a96ffb206498f91 --- /dev/null +++ b/params_shard_269.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:118252e620cb32e74e244f059fc12a06d27dff35c07e6061cb5434716dcb1d13 +size 33554432 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..3201530cfcdc9630e50066c72dbf3e5e2bd45048 --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e15438502ae961a89680427557438357bbbc7bbc03807f6a248e9f9e16c9da35 +size 41943040 diff --git a/params_shard_270.bin b/params_shard_270.bin new file mode 100644 index 0000000000000000000000000000000000000000..ebb6060ef89bdca061c79d28815525554d51cab1 --- /dev/null +++ b/params_shard_270.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bc396d7998637cc8fcb1d2d79161eefd9aec8e9aec645cdee2277f7b8bdc650 +size 117440512 diff --git a/params_shard_271.bin b/params_shard_271.bin new file mode 100644 index 0000000000000000000000000000000000000000..e0ad894e98983ce758bce828b3a5a05e36bbba71 --- /dev/null +++ b/params_shard_271.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e5690e0ce0aad8c8c6bad6efb40cede9cbb6752d7166060675c5e3c01afe767 +size 234881024 diff --git a/params_shard_272.bin b/params_shard_272.bin new file mode 100644 index 0000000000000000000000000000000000000000..1f40e3f3647d7631dcd1585d313861f3107b5a91 --- /dev/null +++ b/params_shard_272.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:266ea1a317894edf60bbc575f496cd3a8b901dcd35b9c872bf52c647736204e6 +size 41943040 diff --git a/params_shard_273.bin b/params_shard_273.bin new file mode 100644 index 0000000000000000000000000000000000000000..a96451ab70bb44515be2abab5dccdf3756a8946c --- /dev/null +++ b/params_shard_273.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:096d5fc0abb078f6c07129c1c14cb2aaf665eab9c83b1fe53bac71ed660c099e +size 33554432 diff --git a/params_shard_274.bin b/params_shard_274.bin new file mode 100644 index 0000000000000000000000000000000000000000..37c7268b255a5299a8246d50f4c40bfac4538170 --- /dev/null +++ b/params_shard_274.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7688c3049841aa607409ea385fc893649dd43465c32a5df0a611e1a8b80c56ef +size 33112064 diff --git a/params_shard_275.bin b/params_shard_275.bin new file mode 100644 index 0000000000000000000000000000000000000000..444195715bdb69b520de743108ba5a14ca8c17ae --- /dev/null +++ b/params_shard_275.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad84ae43be253e30844ac3706750636aed73269a8b6cd8827e36cee5607e7af4 +size 41943040 diff --git a/params_shard_276.bin b/params_shard_276.bin new file mode 100644 index 0000000000000000000000000000000000000000..f852e8f0065f66772466282f57a49fb0c6a7e951 --- /dev/null +++ b/params_shard_276.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fcd12b1edbe10b4b1cb7044fd5cbe2e9867e0e9e567456d86a73422a499f987 +size 117440512 diff --git a/params_shard_277.bin b/params_shard_277.bin new file mode 100644 index 0000000000000000000000000000000000000000..3d33ee942e23dc2f49b294b1fda9955aab7bb0f7 --- /dev/null +++ b/params_shard_277.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa2ebc8db6fd0c9513d1c7e18bb610c12806b790f039ade7eaa786ad5d06c55 +size 234881024 diff --git a/params_shard_278.bin b/params_shard_278.bin new file mode 100644 index 0000000000000000000000000000000000000000..078df0a68adf3a5493d8074ca10c02aec52cad35 --- /dev/null +++ b/params_shard_278.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8716652c4ded8e9f190f8cec8034acf28ceaefa75349ddb8824ac85e36d532f +size 33554432 diff --git a/params_shard_279.bin b/params_shard_279.bin new file mode 100644 index 0000000000000000000000000000000000000000..f29f10cbffecc7f84f6177ef2ba29b558bbdca7e --- /dev/null +++ b/params_shard_279.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af026c3072dfb953f9819da1df105b79fd42ff238ac7862ec05b17fc05b29d7 +size 117440512 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..c31e29786206b40574d7e903a10f9c1726822eb8 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d53a3aa925c48f3fdb2d1505b1d206c38a05273603c4d54f6e81132db23185df +size 33554432 diff --git a/params_shard_280.bin b/params_shard_280.bin new file mode 100644 index 0000000000000000000000000000000000000000..d03df7dbcadeeaac86c8652ef6ff42baeb838846 --- /dev/null +++ b/params_shard_280.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b35900064164494d3ac723dbcbe5a85c2a973c50f3590ee1dd8a8e32ea07c4ad +size 234881024 diff --git a/params_shard_281.bin b/params_shard_281.bin new file mode 100644 index 0000000000000000000000000000000000000000..51ab362539b6979ce0de28b50768b7abd309dceb --- /dev/null +++ b/params_shard_281.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e5646d5bb844f926d48b9c0a1df4e457f882a38515acfc388d7c6ede574f114 +size 41943040 diff --git a/params_shard_282.bin b/params_shard_282.bin new file mode 100644 index 0000000000000000000000000000000000000000..9316660e64c3c3068c6d14a44a365a49685fc187 --- /dev/null +++ b/params_shard_282.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24161b41fb428e59d2433654e42a11748c20f855b20d27f59d217cb1155f3e0a +size 33554432 diff --git a/params_shard_283.bin b/params_shard_283.bin new file mode 100644 index 0000000000000000000000000000000000000000..68cc89dd42e2bf3a575e6bf628885e38415a3205 --- /dev/null +++ b/params_shard_283.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f03d04a63557088a80776936e26c264ac59d4b0c5bd9d59a22d0c4f1164618f7 +size 117440512 diff --git a/params_shard_284.bin b/params_shard_284.bin new file mode 100644 index 0000000000000000000000000000000000000000..b4f3d8dee7898bc1d1203fe31328c1c9713ae3a1 --- /dev/null +++ b/params_shard_284.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:664950513c50cb4a73eb582445388741546de78a243f61228b34c12f2c4bed7b +size 234881024 diff --git a/params_shard_285.bin b/params_shard_285.bin new file mode 100644 index 0000000000000000000000000000000000000000..b59d029403110513eadbc1855bd37e3e6d9da0ed --- /dev/null +++ b/params_shard_285.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ff746ea1706ca7354d33477686192f9176058423f1d5480e3819aeed6ca6047 +size 31522816 diff --git a/params_shard_286.bin b/params_shard_286.bin new file mode 100644 index 0000000000000000000000000000000000000000..7fd2ce6d53ba9881fae548e85ef487964cdd2b76 --- /dev/null +++ b/params_shard_286.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:469a1bc2c04397bd70d7e3e962dd252d6305931df87d6f1db5a39723b8ecb1ea +size 41943040 diff --git a/params_shard_287.bin b/params_shard_287.bin new file mode 100644 index 0000000000000000000000000000000000000000..13e1c3f96feafceb4bbbc163aff3d47883c5d03f --- /dev/null +++ b/params_shard_287.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5472bba202d88f121fc618225cc2717c7fdedfaaf87ab267f35b6483be283ae5 +size 33554432 diff --git a/params_shard_288.bin b/params_shard_288.bin new file mode 100644 index 0000000000000000000000000000000000000000..c94ecbec20c9b727339c59a57bb019ecde0a081d --- /dev/null +++ b/params_shard_288.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f7ff7f2beceb70c892a3dbefbb1a0d4e8323c96e6ca6d32cc8e4679c1c06690 +size 117440512 diff --git a/params_shard_289.bin b/params_shard_289.bin new file mode 100644 index 0000000000000000000000000000000000000000..393edf2d9d268e271bc81e0a87fff01c12a6d591 --- /dev/null +++ b/params_shard_289.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b1f5efa78379bb0538d1d1eddd3766cb3a062b792f90d7de2449deeefbfa1f6 +size 234881024 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..2e57c385a633b2ff57b5cc423a48adc436c89f07 --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23710e74703c6923beb3f44cf4dbeab52dd1ad099010f1fc1fd6aaeaae2e13c8 +size 117440512 diff --git a/params_shard_290.bin b/params_shard_290.bin new file mode 100644 index 0000000000000000000000000000000000000000..18cc76d9edf5e90d2ed6158f9eead8272ee1ca16 --- /dev/null +++ b/params_shard_290.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ab73bb9d78adce30649a5edd9296d4a07e41bb848450df5f099b8a7c64a2a63 +size 41943040 diff --git a/params_shard_291.bin b/params_shard_291.bin new file mode 100644 index 0000000000000000000000000000000000000000..140a444560411f6e4affdb8e475650c9c661f1c2 --- /dev/null +++ b/params_shard_291.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3181a3853454781ef81280f1b683785b0c053aa25c6e90e0f361d702288e803 +size 33554432 diff --git a/params_shard_292.bin b/params_shard_292.bin new file mode 100644 index 0000000000000000000000000000000000000000..dad3d0a29e1dcd31b152b45daf7bcc426f44f236 --- /dev/null +++ b/params_shard_292.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd435f7dfdd7ef5551b61573ba153aa50d4a0555dfcb1114b23f60e92b8be73 +size 117440512 diff --git a/params_shard_293.bin b/params_shard_293.bin new file mode 100644 index 0000000000000000000000000000000000000000..1d9b19bd2e56898879b4cc142e96e73e59f787eb --- /dev/null +++ b/params_shard_293.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c271e108550317bff06fa0b5fcf37a1cc6dffc7234d2cfaab3ec749d3a4715af +size 234881024 diff --git a/params_shard_294.bin b/params_shard_294.bin new file mode 100644 index 0000000000000000000000000000000000000000..32bdd8b0ffd8d275f934b92ef4260926e65059fe --- /dev/null +++ b/params_shard_294.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48631461964159a13c9028f0f054dada500f2a0c0e7b1c2bf6e9e574f4baf89 +size 26820608 diff --git a/params_shard_295.bin b/params_shard_295.bin new file mode 100644 index 0000000000000000000000000000000000000000..a8072f47e14f45b7bae8ebb9f387acb48c4f0396 --- /dev/null +++ b/params_shard_295.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ea2c4e42880fcc358007204b224ba301edf522a174f009fb6e9a38ec707057 +size 41943040 diff --git a/params_shard_296.bin b/params_shard_296.bin new file mode 100644 index 0000000000000000000000000000000000000000..c3469b786682e2c735dbb3ee25bd4a8a1aa68608 --- /dev/null +++ b/params_shard_296.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5aba7d0a91ab241c0e8aa265e72c5b93c13212e5113ca9543fc78d912bc9cbf +size 33554432 diff --git a/params_shard_297.bin b/params_shard_297.bin new file mode 100644 index 0000000000000000000000000000000000000000..0ba46bacdfcd6cdcc757c597260c8cf940d107f4 --- /dev/null +++ b/params_shard_297.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e318fa7aad5615b19f3f06206ea72385b5148ed043fc7d6ebf3254ce25ab0ad +size 234881024 diff --git a/params_shard_298.bin b/params_shard_298.bin new file mode 100644 index 0000000000000000000000000000000000000000..e08864f05ffe3688ecc84644f6c25a2c56582e1a --- /dev/null +++ b/params_shard_298.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bfe25b5a36362d63ecd611dc33e0a97cc8fe23608dc75cf75cbbb95dc471d20 +size 41943040 diff --git a/params_shard_299.bin b/params_shard_299.bin new file mode 100644 index 0000000000000000000000000000000000000000..38fea88654428e03dddd606586d7ec793fc8b995 --- /dev/null +++ b/params_shard_299.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc935f5a678fa44a66db2c27dacf27d6d972647f1ecafe973cf98e46a335d7da +size 33554432 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..0975bff5d69bbe847af21e507046b3483e4396dd --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45914b36a32d58121c76ae9d21e1c269de379031e67962fd7e326fe6bf31927 +size 117440512 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ba29b43f5fe3b4f42f4aa8be28f9373415d43b4 --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a1d5ebd808aac79c048d09ba45c12d9784ad6aed73aaf65c4084830901e3f4 +size 234881024 diff --git a/params_shard_300.bin b/params_shard_300.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc88b26b44150da0ec92e6c07d388b711f8ceb13 --- /dev/null +++ b/params_shard_300.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4edaf4a634f1f3dda011bc132f0f13295cde3313ab92999470c5d72ab8499703 +size 117440512 diff --git a/params_shard_301.bin b/params_shard_301.bin new file mode 100644 index 0000000000000000000000000000000000000000..e0e1c4df88770c3c3c227d5d2c5e8f4c63c17d09 --- /dev/null +++ b/params_shard_301.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60196cec50fc15ef34cf2e423cf02a361cfbf96b37aadbf5709f63ffa2202b7b +size 117440512 diff --git a/params_shard_302.bin b/params_shard_302.bin new file mode 100644 index 0000000000000000000000000000000000000000..0f567b104c32e937360437043d2ac8fa999e78d7 --- /dev/null +++ b/params_shard_302.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f57d461ddf4d4628eaa84b6c630387bf201a4e867b6d1b2a443b2d60253c1dac +size 234881024 diff --git a/params_shard_303.bin b/params_shard_303.bin new file mode 100644 index 0000000000000000000000000000000000000000..161bd7ab31aa763c47e0186fe89c3cc651d94c2d --- /dev/null +++ b/params_shard_303.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae820f8243718268186f06ed13397300ddb96e9f9b910601ccac7c18a4e3ec99 +size 26804224 diff --git a/params_shard_304.bin b/params_shard_304.bin new file mode 100644 index 0000000000000000000000000000000000000000..c7415c7e27a7e7fffab70be3cb2d8f9c7623f488 --- /dev/null +++ b/params_shard_304.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49afc0ad47f01a7c6619781663a6e73519b82aa8ab8cfff864b3c106271dc1ad +size 41943040 diff --git a/params_shard_305.bin b/params_shard_305.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c3fb99f4d8a33c9739348c312c7a66a607fddcd --- /dev/null +++ b/params_shard_305.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20fd4943d509c8b7271bc75e74e8c15ca78109f48dc673967b7f54bd87790d16 +size 33554432 diff --git a/params_shard_306.bin b/params_shard_306.bin new file mode 100644 index 0000000000000000000000000000000000000000..11ae17921e5575e2de9ea8c7128b1334f136872f --- /dev/null +++ b/params_shard_306.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bc7b478ab718bf905397040e22739fb8524b74f07eb64c9f24725ca4e4b47f1 +size 117440512 diff --git a/params_shard_307.bin b/params_shard_307.bin new file mode 100644 index 0000000000000000000000000000000000000000..56801fb6eabb369778712d6670d53985e97de26a --- /dev/null +++ b/params_shard_307.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32efe1cb207cf93eb4281892213131231b61f9f7f5ce25b5821b902b6e3f7df9 +size 234881024 diff --git a/params_shard_308.bin b/params_shard_308.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea4316012c41d9cffd53709e0a8129692baa75fe --- /dev/null +++ b/params_shard_308.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d453d767ef76cecc5df0336527580eb7edd137baf53c52b622cb32365a39892 +size 41943040 diff --git a/params_shard_309.bin b/params_shard_309.bin new file mode 100644 index 0000000000000000000000000000000000000000..b5647547376041165fbd1f434aac2376e50fc0eb --- /dev/null +++ b/params_shard_309.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e27ba4ebcf9bbf182e6f83afdb8cb08dbc8638491ce543077fbecbfdcc39e0b9 +size 33554432 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..758ccff25a3f97379784d50da998198d97686039 --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dc784bcb26912b6a860313f267dae45b497bbf9fcaf89fed5db3570183b2860 +size 29163520 diff --git a/params_shard_310.bin b/params_shard_310.bin new file mode 100644 index 0000000000000000000000000000000000000000..1a893e7400362d359903a3bff1b2e4d912758cc9 --- /dev/null +++ b/params_shard_310.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9e5cd10d7ef3fab42570e00adbc4360777dcdf94eca237f51221c179eda9e1b +size 41943040 diff --git a/params_shard_311.bin b/params_shard_311.bin new file mode 100644 index 0000000000000000000000000000000000000000..fafc95888f910f98d5bddc3c741a6f3a964759d5 --- /dev/null +++ b/params_shard_311.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1de9ffe4ec058d10cdf662bb50eaeede919aa2b6ceca023aa77f41ed1c960600 +size 33554432 diff --git a/params_shard_312.bin b/params_shard_312.bin new file mode 100644 index 0000000000000000000000000000000000000000..eb26fb4d975f8e8ac99b9985f23b4acfadb663d7 --- /dev/null +++ b/params_shard_312.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e20aac8c41126ead28e4a6d0315c3fa28bec947bbc82510bb8f922fe74944f3 +size 117440512 diff --git a/params_shard_313.bin b/params_shard_313.bin new file mode 100644 index 0000000000000000000000000000000000000000..28239516c3b630e44da942a4e14d3ba71e0bb519 --- /dev/null +++ b/params_shard_313.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a88fd063e9c39fecd295256a4184b02fe9dd71d62f330109f15231bf91fa6dd +size 234881024 diff --git a/params_shard_314.bin b/params_shard_314.bin new file mode 100644 index 0000000000000000000000000000000000000000..937f0c86960bce7386d739081b04be069ec871c1 --- /dev/null +++ b/params_shard_314.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab05e3c1b4d00ab18d0642b26dbec681c94d38c65bd3594bdc0da82f0ec4ef1f +size 29163520 diff --git a/params_shard_315.bin b/params_shard_315.bin new file mode 100644 index 0000000000000000000000000000000000000000..e893d80ae62b0e255f152edb9d20d41cd9adc1c8 --- /dev/null +++ b/params_shard_315.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d8ebc7a577db176ddc8101eb4b4fafa523a8b6daaca222fd0755ccec8e5b61 +size 33554432 diff --git a/params_shard_316.bin b/params_shard_316.bin new file mode 100644 index 0000000000000000000000000000000000000000..d11629fb5ac229b3761cee723a7597e120e0bcb3 --- /dev/null +++ b/params_shard_316.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02263ea53e4192184e6fb8f21a3eff758c1c386434886d20c07b9345e0a7cfd +size 117440512 diff --git a/params_shard_317.bin b/params_shard_317.bin new file mode 100644 index 0000000000000000000000000000000000000000..89b8f4c7701d464645042c13414aaed2edd2415b --- /dev/null +++ b/params_shard_317.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92086146b8543d2c9161c7e6b70c676504804b8b2eb04e51474a8e5f9a97f149 +size 234881024 diff --git a/params_shard_318.bin b/params_shard_318.bin new file mode 100644 index 0000000000000000000000000000000000000000..11b31029f460f18d463128f76f9859524cf07bfd --- /dev/null +++ b/params_shard_318.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47cad9ea2218ddc52ed01b5838948f44accd4ba243e37e5c1d7faefb2daad761 +size 41943040 diff --git a/params_shard_319.bin b/params_shard_319.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c6b6c2ddf5389e76302cb890c5e357a419b00f1 --- /dev/null +++ b/params_shard_319.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c2cd91769ef3bd39ee212186aa5da01bdad54469ac9d21323fe51734e99af36 +size 33554432 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..d1fa4490e73e83370a041a3e5b91c7187b417f73 --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:353d1ebdeb8cdba8ac3f85084d3e209938a4ce9592489b5433e7c38d720cd988 +size 41943040 diff --git a/params_shard_320.bin b/params_shard_320.bin new file mode 100644 index 0000000000000000000000000000000000000000..b23bb65a3bacf6af91eb67439988fd7f7e903aa6 --- /dev/null +++ b/params_shard_320.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee6433607e0c9f450058916667203fc89d525aa95616886afe04af3d75e1e329 +size 117440512 diff --git a/params_shard_321.bin b/params_shard_321.bin new file mode 100644 index 0000000000000000000000000000000000000000..209e02b851ba1a829868d58e2035c415e63cae69 --- /dev/null +++ b/params_shard_321.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df5961b9c033313ac0fdf946686189247f5a99dd48b2ddc56801823d33afe281 +size 41943040 diff --git a/params_shard_322.bin b/params_shard_322.bin new file mode 100644 index 0000000000000000000000000000000000000000..699c05d804e7bd515c4f2443d3e68b59ff3c80d3 --- /dev/null +++ b/params_shard_322.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528e845b4c98044c6b7706299a711136219e8cd76414fe296cf02a523da08172 +size 33554432 diff --git a/params_shard_323.bin b/params_shard_323.bin new file mode 100644 index 0000000000000000000000000000000000000000..705b21d3e54373e40508f7f8c9dc95af663d11fc --- /dev/null +++ b/params_shard_323.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b500d4ca470e91f914f29a699563f73c87d2df91982dfea6ea8d3463f8f1ac0e +size 117440512 diff --git a/params_shard_324.bin b/params_shard_324.bin new file mode 100644 index 0000000000000000000000000000000000000000..512e50646fc69c9ce22bdff56867099d9106f7db --- /dev/null +++ b/params_shard_324.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe231a4a11d3242bba4f9698e99fb84c93ccc6e0fe6dbb550e25cb3f2e457d5 +size 234881024 diff --git a/params_shard_325.bin b/params_shard_325.bin new file mode 100644 index 0000000000000000000000000000000000000000..0656bd3d9efed27b77bdbc1cc5c4b08c1485d4e5 --- /dev/null +++ b/params_shard_325.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:779c9c9247e2df34a09db4364d2870acd1aa1b1bd0e5e44215a166955a1b8958 +size 31522816 diff --git a/params_shard_326.bin b/params_shard_326.bin new file mode 100644 index 0000000000000000000000000000000000000000..97ca25970c4511a0b9041422ff858076946c48d9 --- /dev/null +++ b/params_shard_326.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4006906596637040dad9def6db3ef02b1d6e9cad1112bcbef599ce7b28d94145 +size 117440512 diff --git a/params_shard_327.bin b/params_shard_327.bin new file mode 100644 index 0000000000000000000000000000000000000000..b0f21189a180e5908ab1091baf582d540655edb5 --- /dev/null +++ b/params_shard_327.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076ecd987aec9af65022e9d0a6e3776166b360f7895b5ddb8306036b6c617d93 +size 234881024 diff --git a/params_shard_328.bin b/params_shard_328.bin new file mode 100644 index 0000000000000000000000000000000000000000..bad8c78af1412edfc8b142dbc3e8b7c3d11ed2a1 --- /dev/null +++ b/params_shard_328.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65b2a2633b93095fb94dd54b6a40e4c223a5c625cda23ed766323b1d44e373eb +size 41943040 diff --git a/params_shard_329.bin b/params_shard_329.bin new file mode 100644 index 0000000000000000000000000000000000000000..cb4569c06db42693fd42d4c146f6753f906fccc6 --- /dev/null +++ b/params_shard_329.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a02202261236f19a30cd6f3b4327ead204c6074e57f5f3207762f944488c1b34 +size 33554432 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..81190655e0ad632a3181195870200d479b735a2b --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07c1e4a06a8374658b66ea7cf8dc0c186be0dfb53baf64313f119122c6483ffe +size 33554432 diff --git a/params_shard_330.bin b/params_shard_330.bin new file mode 100644 index 0000000000000000000000000000000000000000..1068d2e7fd2899b2d39f5231068855d702b2f184 --- /dev/null +++ b/params_shard_330.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c0087ba3830cc070efcdab85d97aa93af0023f7cee2d4776f2a261ba5bdea4 +size 117440512 diff --git a/params_shard_331.bin b/params_shard_331.bin new file mode 100644 index 0000000000000000000000000000000000000000..cfd5008cce47c11189caee4f4b2edc20998a9aec --- /dev/null +++ b/params_shard_331.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff10dbb4499e16fa644c2cdccc53870e1dd0bd17d8a252800befcde0b7c095f +size 234881024 diff --git a/params_shard_332.bin b/params_shard_332.bin new file mode 100644 index 0000000000000000000000000000000000000000..74ef3c9dcbcc408dd25e90b217cdda5287273310 --- /dev/null +++ b/params_shard_332.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2af9079c751bba0c445a762fb87344769b903bf3a9ad7cc4979443326346e14a +size 41943040 diff --git a/params_shard_333.bin b/params_shard_333.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a488a587d082a52a083a80078f3ecef29b01379 --- /dev/null +++ b/params_shard_333.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e8be33964110baa45881a874ae08c44cff318e49e6401dfbe330543c73e397b +size 33554432 diff --git a/params_shard_334.bin b/params_shard_334.bin new file mode 100644 index 0000000000000000000000000000000000000000..8e8ebe9c715a870c3f9add6615a0e320f1c21dd4 --- /dev/null +++ b/params_shard_334.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d378356c978596135f9cebe5f9d7a1375b8c3ab0072a320d27332a35cfe0a5 +size 33112064 diff --git a/params_shard_335.bin b/params_shard_335.bin new file mode 100644 index 0000000000000000000000000000000000000000..59b995be4e55f2f05a22793eeb268f74956ee12c --- /dev/null +++ b/params_shard_335.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dce08fcafa763bc624b152b2b1d4b219bc75c445e226be153f21cf9eb262cdb +size 41943040 diff --git a/params_shard_336.bin b/params_shard_336.bin new file mode 100644 index 0000000000000000000000000000000000000000..9dadfdc6ff02ccba612db841c2ef26d67d552988 --- /dev/null +++ b/params_shard_336.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c50a18ebcd4080e4a7fbad5932cdf092388d8bfd14b61eaf14502d86b909269 +size 117440512 diff --git a/params_shard_337.bin b/params_shard_337.bin new file mode 100644 index 0000000000000000000000000000000000000000..983b535b23c37e61dadd9b581914a85036d724eb --- /dev/null +++ b/params_shard_337.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07b97253df95624c21dbec1e6cdb85a1bb65279510cc8ce8a622210a169a4918 +size 234881024 diff --git a/params_shard_338.bin b/params_shard_338.bin new file mode 100644 index 0000000000000000000000000000000000000000..6af59c5bb9e197f99b5336c5f6a31c9962a3a98d --- /dev/null +++ b/params_shard_338.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17bc64d8d8f80cff6d6effa62ae6479c88360321d320f0f04d3642965dfbdc29 +size 33554432 diff --git a/params_shard_339.bin b/params_shard_339.bin new file mode 100644 index 0000000000000000000000000000000000000000..f61d50abfaab2683f5f0750e59f9d2501e52c725 --- /dev/null +++ b/params_shard_339.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec7f14c8569ecd2738bc753d738d758f4b9b2a6d56b62d6d6d3f684e92b7187f +size 117440512 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..4baa0903e9ddd69e8b4fe10b9feec72b836d5c3c --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:455fb38a6bcdb916815a0b5531c6996773f29075bf1de8c8174bcb2dc5a56e21 +size 117440512 diff --git a/params_shard_340.bin b/params_shard_340.bin new file mode 100644 index 0000000000000000000000000000000000000000..318b2f30cdc4196b4a061b0a100c39d946e56734 --- /dev/null +++ b/params_shard_340.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e233fce642684778faaa003313c2eedcd61de8494014405bdfec71d45edf4bd9 +size 234881024 diff --git a/params_shard_341.bin b/params_shard_341.bin new file mode 100644 index 0000000000000000000000000000000000000000..18a39b6191371284e25a39cf63618cf6ba0f87bc --- /dev/null +++ b/params_shard_341.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e5b520117b38111fe04daf648e8d603558bba288aa4ff9e5ea1342ab700989 +size 41943040 diff --git a/params_shard_342.bin b/params_shard_342.bin new file mode 100644 index 0000000000000000000000000000000000000000..45bff9b6a07393e9acc505cd128817d5e8f72836 --- /dev/null +++ b/params_shard_342.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816ab0779be1ba0b3d44f61496e242009b1761746944fc608ce94f679e5056b7 +size 33554432 diff --git a/params_shard_343.bin b/params_shard_343.bin new file mode 100644 index 0000000000000000000000000000000000000000..73f5c20f7c5973043fd469300587bdfd52868c1e --- /dev/null +++ b/params_shard_343.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8243868de5e57a34905067364cf9bef27cd631fb61621954d3f5ebc4292b6a61 +size 117440512 diff --git a/params_shard_344.bin b/params_shard_344.bin new file mode 100644 index 0000000000000000000000000000000000000000..061938ff3e9a5a3d5a9247fd27d1f4adde022481 --- /dev/null +++ b/params_shard_344.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c9b54f54c2297523116ab82db674ef48cfb24f2187c19f2af752275834bd3b3 +size 234881024 diff --git a/params_shard_345.bin b/params_shard_345.bin new file mode 100644 index 0000000000000000000000000000000000000000..9dc6fb97911818245a3869d6ef33cb6c5733ee2a --- /dev/null +++ b/params_shard_345.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8965473a39592547bc901f371d4bc6c2b0c8ca38dab27fbfb1edec23c5d9bab +size 31522816 diff --git a/params_shard_346.bin b/params_shard_346.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbee1e1e1379bb22d0e0460fbf0a9a279949cd13 --- /dev/null +++ b/params_shard_346.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924f065269b4ea658709a8f8772e4bdb1328a8dee15392828c0117a0968b2cb7 +size 41943040 diff --git a/params_shard_347.bin b/params_shard_347.bin new file mode 100644 index 0000000000000000000000000000000000000000..733d280e42492befaf8681f74ce41d707c445ea4 --- /dev/null +++ b/params_shard_347.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:362afc876c94ec1f9ec8a73ce295eeae2eff6a8ba3e71da7f181d4cf840db02b +size 33554432 diff --git a/params_shard_348.bin b/params_shard_348.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0d936a6c9b43c24268f3cab03b810640643ca49 --- /dev/null +++ b/params_shard_348.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95a29761309317cc707635842e939f1a3fd3d664dd3e835e4a9385efc7828f70 +size 117440512 diff --git a/params_shard_349.bin b/params_shard_349.bin new file mode 100644 index 0000000000000000000000000000000000000000..04f9517f7298e34e1fbed269fba063555a9df431 --- /dev/null +++ b/params_shard_349.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:affa7284b8bd21066fc69fce2d8c1e5ca1944276b14084766e00dc93cb22983b +size 234881024 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..e14ada874078db71e8e27c1a2706b872c9e0bc67 --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7375d46970f8150f01387dee3978944e199179f3fc6f81139860c858a551a103 +size 234881024 diff --git a/params_shard_350.bin b/params_shard_350.bin new file mode 100644 index 0000000000000000000000000000000000000000..911d0af65fa20186c352399de95af7b3e972049e --- /dev/null +++ b/params_shard_350.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6caace2dbaa413ea41672f8ac9f96f525276f8e6aa2e700ec42766e8353bbbb8 +size 41943040 diff --git a/params_shard_351.bin b/params_shard_351.bin new file mode 100644 index 0000000000000000000000000000000000000000..8a952c5d30ca8fafa75f076a4b1968a65ac0f92c --- /dev/null +++ b/params_shard_351.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e840d4e3bf4eea811a1148a9c71d1bd265515f7cf77c12894d9f0a6a62b7ce7 +size 33554432 diff --git a/params_shard_352.bin b/params_shard_352.bin new file mode 100644 index 0000000000000000000000000000000000000000..e9e9cda9f20e95288c37721b72891f5465791a4e --- /dev/null +++ b/params_shard_352.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c4c286aa44184fa8e6c61fe5853beb89fda494bcd2fa3380bdf7aa750d6c94 +size 117440512 diff --git a/params_shard_353.bin b/params_shard_353.bin new file mode 100644 index 0000000000000000000000000000000000000000..71019cea6b4c84fd5f9455bbf71dbd50342a16fa --- /dev/null +++ b/params_shard_353.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d138a97a4ce190f81dacfe2ac3d6f9880865c91510ee35f8c78cf08163d0891 +size 234881024 diff --git a/params_shard_354.bin b/params_shard_354.bin new file mode 100644 index 0000000000000000000000000000000000000000..23751e49674b18b191ba990fa0c0dcdc5083c117 --- /dev/null +++ b/params_shard_354.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eb2a42bd4763e4bd64bf4318defbd9362396647b373f26b967191bf98bf992f +size 26820608 diff --git a/params_shard_355.bin b/params_shard_355.bin new file mode 100644 index 0000000000000000000000000000000000000000..21991cb990e7ce2c2c183af45cde8a50d8da1d76 --- /dev/null +++ b/params_shard_355.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:578c419440010a8771923bcc60b03f8bc295391c872b76d88baebd5a03889480 +size 41943040 diff --git a/params_shard_356.bin b/params_shard_356.bin new file mode 100644 index 0000000000000000000000000000000000000000..4668cc4621519cfa9a7bd39267cb0ff3d0ba29e7 --- /dev/null +++ b/params_shard_356.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26c40d6bfe2c5a7e307bce65c621c90e4affc025366536838f18b8e0a085082f +size 33554432 diff --git a/params_shard_357.bin b/params_shard_357.bin new file mode 100644 index 0000000000000000000000000000000000000000..b750000cea319b76a34315e4268fdb73db5b5470 --- /dev/null +++ b/params_shard_357.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ab346ba7314628b8d0d7b36d6f5f1f3439af6a5343edde27e430a2fcbf1613 +size 41943040 diff --git a/params_shard_358.bin b/params_shard_358.bin new file mode 100644 index 0000000000000000000000000000000000000000..06552609797a182a860ad353d62dc31c98d60d4b --- /dev/null +++ b/params_shard_358.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df55f0500d6654dfb7280effa028cec883ca989c5c38d5d04e543e4cf614035 +size 33554432 diff --git a/params_shard_359.bin b/params_shard_359.bin new file mode 100644 index 0000000000000000000000000000000000000000..a7323d1ac5c36bf0099d6e248b7637cd647be364 --- /dev/null +++ b/params_shard_359.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634f6fcdcc06c4a47d603a61fbdc91456ca079858c67ecb90dd112559df975f1 +size 12075008 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..d5527d90d12b2d9c71add6faa970b042bc9a8534 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9c111200fa1216416497bac9b7257ec2c8bbc78e29e2e93772f55040f2b80fc +size 41943040 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d0535c71538340347a26ed8974fe5ae183511b1 --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac41a850ffe300556ed4c0e445f46314454d37de85760b46058b55cdefed5864 +size 33554432 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..d5b9c6911cfe6f4c1653cc4badeb21659c2c0371 --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c69042596df5756b07f84f6320165c747872119fa1c9bc3b220feb95465fd796 +size 234881024 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..31cd9670cb4018c0776ff33b92b967844cb186d2 --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cedbb5607cd5ddc429ffc892059b270eb117219c2f5cafc0ee5d6e373f73bc1b +size 41943040 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac3ba7266dbc88e7f7dd20d32d87ddcb0de4a5f4 --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc836a886588f4475723bc7506ba52f15313abd12d9777bbfc7ee32df9c21944 +size 234881024 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..0c9c7e142a54c9d1929e58c3c0b2fedfc7b880b1 --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a4573c8f196c3dd8328438e334c82f51a1d47d5b9d6b84b6c5d38a928253126 +size 33554432 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..39e66c30edbd3cdf878aa1cb3adbcbe4cc94e159 --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8be6b08127e0c68cc59e0423e71e201edd1c17522c7b803048253581d85350f +size 234881024 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..1dce950ca6244df58d90babe77e749e38a77e464 --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee3f8d0c41c4b073c53855acab62e8e5344653f92b6752ff31fc1343d35db4b4 +size 32833536 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..39685476a56ba1f032ad519c19abe8a74e2c6091 --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a7b92868462433c76232fb6533f5bb977e38e3aefcf6344032d68676ca394d6 +size 117440512 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f20df58dabb026fd457c55ab8ce35e32e902694 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9590fb4c3d12d1183438898424368a5b9bbd6928633b8779d31c9a685de02e +size 117440512 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..98494185e89f8d16f664c28207516e4bb26ded67 --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69db0677f96e0077aa0992829651dd87bef22c84780ebcd59a1fe8f139e48c3c +size 234881024 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..d57723bf42d6cd8403e003602208bb68cd6f032e --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f123f6f8006b5381cc95298d04aea0f221b9f615251573990bfba8ddc145e5cd +size 41943040 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..ace4540fcc852c3306f2b2fe8c05049b029b6279 --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1875cf1cfa43a7d82a265b1c27ab48f529b71d8ed8ffe1c6d003c3aaa81c10f +size 33554432 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..77077c7af32edacb25bfc4816bf7d0039cb60c73 --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df6534c00610207e9acd265a1ce639727ac006e844adff2c325bb517d31ba309 +size 117440512 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..431bac38bcee27d2f30b2d1ba32b1641c36fcf5c --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b5bd6230afe30d970d26f8611fcdc2b919bc112f02c5962ad882d471b3703c +size 234881024 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..5abf3bfaf33fedd4aee18a748c1a888540b324ff --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de5c87f9c4c8c1dd07e96559d87a67a192881c54e68b914e8819f6e6a490378a +size 31145984 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..b0a3b7254b45fd332063d38c1f34b8563290734f --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:353804b6de3c388476c8be0aed8bf627e869e4afc6be58cb8b6310202b88b188 +size 28147712 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..f54d7e66116de6bfc263de5d8799e82b04106b36 --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f76635466fa21650a594528b79c10c9b04259fb0f486c1c671c2b81fc3dba69 +size 41943040 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..66040feb31df9a4fe53242c2f0bc166100ec5a2d --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5df3e678634cc497f0b149ee29fb39772417f06c62976b1b09a4fb1285d2a50 +size 33554432 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..e99abf120a6b3400575dbcfbe5dfc04aa37fefc1 --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6de8f7eabd780fcd5b086adf3623c560cd527d1ff28a64db297ed452d2527a75 +size 41943040 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..fd6827796c50cf8adfdcc0c218da22713a8a57d9 --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:626dd19b18c0d54448f3cae1a6aae0775a20ad2918cf18e022b45539c097bcc9 +size 33554432 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..33a42208a57a38efc534c8f6d526ee88e515f988 --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfdc7c8a953a75910ff2df1744a61e88842842bdb23020fbf49e154d2bfe6511 +size 117440512 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..9783d077035b5628fbbbeb2208fb9189327ee126 --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b9ecedd529a970c5d34201fba4052b5e1498037bcc992bd8d19d61ff72970b +size 234881024 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..00dabb791797acd50053c87a71b20e220f64b86d --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd8d18883f229066154361abaf0596dd7f7b0569e4fecfed18019d5db226cf1e +size 117440512 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..ae3a4ea9c939b2bebb62ac054fede7de54b2af77 --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79779fc4b8340df025ef880c5d3f83774f923fc22f869bc4dcc983fb24dafe8f +size 234881024 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..6eee2660db42600d98f6aea255999fe594da8480 --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04696a3f9034488406b3154461401ba774a66c7cb8fa8714a7407dc08dee1416 +size 26804224 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1626e494088e5663e82b014e222728b906b5b19 --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f320ac6d12e33f55d31e02fa950f4c8254ff39d4d24cdc904177d607abe95b0d +size 41943040 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..011c43136a36909beef20d00bf493c425bd5cd6d --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f47dd5d04ce55c475109fd8a63482a6826b7f5704e323fdd15479db245b3d6a8 +size 41943040 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..e901b3f8a570af81e2e6ad8324e3e8f2dc90408c --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c4e07cde2ba4a526bce8adf496ce50f4eb35fb22bfed2e7139e06b707ee33f0 +size 33554432 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..317dccefffc1b048e57149cddcc03b373b07c664 --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:209512b0235c69181422ba05b85e5d22954d68e726e6e91bcf5924d6a3a78757 +size 117440512 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..d5f7e63e7fda2b025b856b6dac417fc6a49d40cc --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0199fb79f108f31e2c273b55c6a9969399e9a89b77b9a39d4d6fbea6e8f2c6e +size 234881024 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..8e3c563498d162bc4d4ea63e83a02e314f779e15 --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9eb507d6c24ec8888550108da98c65b3599696ee2e5400ff98a0ff69a9b7edc +size 41943040 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..fedf7fe090baf624c504431f4ba85e3ad70561ed --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5fcfc88afcfc6fc1198d2fef8d68167ae9b233e220fa05b9117e4c623a55d3c +size 33554432 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..532d46922201473700f011b374ad4ebc0dff7e12 --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26c123519aea722a4afbde50565fc5ea369dd7ef9d9bcff5a7551846e740bc68 +size 41943040 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..d3e4529e81d9daee672e0c01ef10e6511e0bd896 --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39be3f5e70d0a0b28341743fcf57bd3fc61b3d16ba6f28288481e4b3f0defd2d +size 117440512 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..d9e1c0bfed25540c5cc7d387fbe2d5503503dd6d --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4264e40e57cff75850919d6309dd4d048fe799863cc3d8425a139b3370957749 +size 234881024 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd7b119ce0dd349bd70acac658d44cf78707a90c --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0826e6f081c7a5dfa9b9447603cae5f34bbb3514c173ee18888e068dfebe089a +size 28114944 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..12e0f27a4ee1b0153ac147daed885d5c98a92642 --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7c60167a89cad1e24e7a9346262628c498c6a7e908267987e0b701f6b7c94f0 +size 33554432 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..1eb6c36186390e754eb85d8bf24555962ebf3b28 --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a54601c267a6db94a25f9494f87ff1df2ace9c72e0184f2f0c6e60911d29843 +size 33554432 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..7f771ae4502c2837f6cc7c2cce02f7b6423d54a5 --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e8debf11eefbf94b27cd9536534d26494098fc6463720446724e7d1df04fd4b +size 117440512 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..d5e506715ea7b50136231aa4b954ddd41d038b24 --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c69da1bd7c07843661291af4bb06de160b76cb1f9427f4dbc6094ff0db29d06 +size 234881024 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..3af7c7225fa44d9294dfb68e9f24f482bead7d97 --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d0014fcea13313f1e955e4803b333b24ff5714d6d8de883380de18b98b67c5a +size 41943040 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..f99c412f345e15bb067cb49a6bf39940209cfc0d --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6794866a7b75957b6c261daf56df3428e888a43b4b9b6b12faa0ca7cae8d36b9 +size 33554432 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..07f8c74fca3ce957b44c603956c982e7292ff35f --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14eac61a16f997f74f20a255776124ac044571958e7cef2adc1b38d6fcf841fc +size 117440512 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..079ecc9e5f12be65ddc1affebf21280d649a01a9 --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e6c1bca88f323605da3da4a5d64be8a715cc73c7aa08ecb739defef2c9d4c4a +size 234881024 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..669c1db7d7bdb8a53b63052daf574836b9813f32 --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9ebd51bbf55e20ac30061481c4c7e62f3cf18f5cb760dbe67198f8fb4cc9bd1 +size 41943040 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..b81c78a390c8a8cf2401a77f9445686dbbd0f7ef --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734d855655a6e57d54e5794c213a0c7e4a25f5d4493f9a97533a1d2793911419 +size 32817152 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..f3277942f8f69aff5de8cea16edfbc035da29f98 --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5dbcd744735c530414259ca5f8742db68fab3eb224cd97e1c8461c1ff38a3f +size 33554432 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..494478da6d662f0ea6fc2781fcd879e466ef44e3 --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d07a3fc2c8957fa5679266a9e7a2b7b03c884ef42743fcdbcf78f01340dd414 +size 525336576 diff --git a/params_shard_80.bin b/params_shard_80.bin new file mode 100644 index 0000000000000000000000000000000000000000..42274b055551f651069a5c147dfe1d5e26f9c16a --- /dev/null +++ b/params_shard_80.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2abdf40b96284cdaa74b1b3be2e19db00421ee10397f91c48e5e0f6b8ea06785 +size 117440512 diff --git a/params_shard_81.bin b/params_shard_81.bin new file mode 100644 index 0000000000000000000000000000000000000000..e1a30b0a0baf4f87e09548590cefa3c7bf449c51 --- /dev/null +++ b/params_shard_81.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aa7c054dee96e46a0109a11a38bc090c6de5f2262012517ae732fe638e83ef1 +size 234881024 diff --git a/params_shard_82.bin b/params_shard_82.bin new file mode 100644 index 0000000000000000000000000000000000000000..6c4b8373d7285465a2d46091217647c287ac454b --- /dev/null +++ b/params_shard_82.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf60890735ac06db402b6474ee9c1137b89a5fe69dfe0b9d5545a8b55789787 +size 41943040 diff --git a/params_shard_83.bin b/params_shard_83.bin new file mode 100644 index 0000000000000000000000000000000000000000..e43f8922454232615550cc3c5420c79c00d06794 --- /dev/null +++ b/params_shard_83.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61aa5e5086ea8d292bf6df06ca9fb4e7d91f0f2dd69ce7a606fdb3ae114df53d +size 33554432 diff --git a/params_shard_84.bin b/params_shard_84.bin new file mode 100644 index 0000000000000000000000000000000000000000..e10d00e4cff85534d162bac98a0b256a598594e6 --- /dev/null +++ b/params_shard_84.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e298aeac4d9f904644bf02b38eefa268fcf0e654a7e74401304d7e8839d95fa +size 117440512 diff --git a/params_shard_85.bin b/params_shard_85.bin new file mode 100644 index 0000000000000000000000000000000000000000..c59edae86167acf6f2d6007bd63f7be8dd693269 --- /dev/null +++ b/params_shard_85.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a88f75a50e2aea9025f5f9ead35068dfa3bedba5525c9de1dca8f608e477981 +size 234881024 diff --git a/params_shard_86.bin b/params_shard_86.bin new file mode 100644 index 0000000000000000000000000000000000000000..45d53628f476babf3734204094f88c28bc88b501 --- /dev/null +++ b/params_shard_86.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b0a6a86360d9d32d4fbd02df98f981dff8e7d269d795800c3bfd6a8491d8900 +size 41943040 diff --git a/params_shard_87.bin b/params_shard_87.bin new file mode 100644 index 0000000000000000000000000000000000000000..c8f0ea6a64a2115401e4f5a26d6ac3c9213945fc --- /dev/null +++ b/params_shard_87.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e955a0d43db86c6e15cb94bd26c3bccf0df17947a30af0241b345ac323137568 +size 33554432 diff --git a/params_shard_88.bin b/params_shard_88.bin new file mode 100644 index 0000000000000000000000000000000000000000..477e37d4685068fc4632cf7414ad273e42c6c219 --- /dev/null +++ b/params_shard_88.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ffc67175143efafeb384eae547375ad9d56a963958bb76c415a124a2d215e77 +size 234881024 diff --git a/params_shard_89.bin b/params_shard_89.bin new file mode 100644 index 0000000000000000000000000000000000000000..d5ba90b211c1d3ef6afea2727e7a66bc1a02289f --- /dev/null +++ b/params_shard_89.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c79a5faef4e6a5570d34a057ca15924f03e7b2df43df72acf21648c3b6cd2c00 +size 29196288 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..f71a82de639b1433806e6541f852890cd3f3b48a --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43739f3c1a5139be26e579f9606203b5d04a84649eba3df105f8c7168baff734 +size 117440512 diff --git a/params_shard_90.bin b/params_shard_90.bin new file mode 100644 index 0000000000000000000000000000000000000000..e9d91995d351dabdab2772c2eb790482e4b4d57a --- /dev/null +++ b/params_shard_90.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bbef7a51595e9999ed81df769c587074e048b7bde8789c0da28279e5f0a6d36 +size 41943040 diff --git a/params_shard_91.bin b/params_shard_91.bin new file mode 100644 index 0000000000000000000000000000000000000000..9fb7985ebe33b759a864eaac9cdb15101465e4a4 --- /dev/null +++ b/params_shard_91.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:019359b46545efff0d2ad77ce48333623bc2539e13563d42705770c6b5b1ac1a +size 33554432 diff --git a/params_shard_92.bin b/params_shard_92.bin new file mode 100644 index 0000000000000000000000000000000000000000..9bf97466d8aa9fa6f6d1a3fc719e0924826e4972 --- /dev/null +++ b/params_shard_92.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37ead1f9dd906f1a450d6a9cec1f21ff9e2330b0e271c504e8eb875a978ba25e +size 117440512 diff --git a/params_shard_93.bin b/params_shard_93.bin new file mode 100644 index 0000000000000000000000000000000000000000..d8fcc59c403bbab2f70aa25233c294ee32292623 --- /dev/null +++ b/params_shard_93.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a762cd66d4f415eaa8427313a7bda952f856d190ec1cf33aede8748bf84d808 +size 117440512 diff --git a/params_shard_94.bin b/params_shard_94.bin new file mode 100644 index 0000000000000000000000000000000000000000..117545469f9900d9762fcf40f0b5303df1571c44 --- /dev/null +++ b/params_shard_94.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d1626ee8537e0afbbce0b5d188451e233c475127a89e6250eab45024fa8f578 +size 234881024 diff --git a/params_shard_95.bin b/params_shard_95.bin new file mode 100644 index 0000000000000000000000000000000000000000..d6014337897706eb91293daea13b3b2a85b50fdc --- /dev/null +++ b/params_shard_95.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff891d8f7b54fc4a9d49d5719cd3351a73168b7bde151fb8e38b81756b02c17 +size 41943040 diff --git a/params_shard_96.bin b/params_shard_96.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b7a6ee7dabb65508ebdf83c4437d4eb4e6ede3c --- /dev/null +++ b/params_shard_96.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74222e720a57c22cdd1abfcea3429630dc7b5ea38e304c49a791786414213b85 +size 33554432 diff --git a/params_shard_97.bin b/params_shard_97.bin new file mode 100644 index 0000000000000000000000000000000000000000..15904d3b129d86dcf18f5d7ebba70e6cff406bbf --- /dev/null +++ b/params_shard_97.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6c4db5ed68bb0d60ea32601e06a2104a3bc6b990b7fdfdf30773abec952dda +size 117440512 diff --git a/params_shard_98.bin b/params_shard_98.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b9b7d83364e6247c020d46b06df5d568d1b21e0 --- /dev/null +++ b/params_shard_98.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f750a22d1fafac5a1f6395ab616fdeb01bdb559fb260e0e8a80d732e752496c8 +size 234881024 diff --git a/params_shard_99.bin b/params_shard_99.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ca6fa12627c2f6ba86999d815d867f0feb5e74b --- /dev/null +++ b/params_shard_99.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cceafc63d8cb067157d087757b7049f194b8d126ea2448d6dbeb773790eefa32 +size 30490624 diff --git a/private-llm-config.json b/private-llm-config.json new file mode 100644 index 0000000000000000000000000000000000000000..0fdc034341d0b1f8ccb19ff6471c501e74f31fd4 --- /dev/null +++ b/private-llm-config.json @@ -0,0 +1,55 @@ +{ + "model_type": "llama", + "quantization": "w4a16g128sym", + "model_config": { + "hidden_size": 8192, + "intermediate_size": 28672, + "num_attention_heads": 64, + "num_hidden_layers": 80, + "rms_norm_eps": 1e-05, + "vocab_size": 128256, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "context_window_size": 4096, + "prefill_chunk_size": 128, + "num_key_value_heads": 8, + "head_dim": 128, + "tensor_parallel_shards": 1, + "pipeline_parallel_stages": 1, + "max_batch_size": 80 + }, + "vocab_size": 128256, + "context_window_size": 4096, + "sliding_window_size": -1, + "prefill_chunk_size": 128, + "attention_sink_size": -1, + "tensor_parallel_shards": 1, + "mean_gen_len": 128, + "max_gen_len": 512, + "shift_fill_factor": 0.3, + "temperature": 0.6, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "repetition_penalty": 1.0, + "top_p": 0.9, + "conv_template": "llama-3", + "pad_token_id": 0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "tokenizer_files": [ + "tokenizer.json", + "tokenizer_config.json" + ], + "version": "0.1.0" +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4fd26877f22f3a80ec2f4f83f941857317c6f43b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "legacy": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}