{ "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" } ] }