{ "metadata": { "ParamSize": 805, "ParamBytes": 39688355840.0, "BitsPerParam": 4.356224340918386 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 525336576, "records": [ { "name": "lm_head.q_weight", "shape": [ 128256, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 525336576, "byteOffset": 0 } ], "md5sum": "b3f29ee97aadd1c541db79d9e7f3ebcf" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 65667072, "records": [ { "name": "lm_head.q_scale", "shape": [ 128256, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65667072, "byteOffset": 0 } ], "md5sum": "b0e199832ff5d572aaf5a86f25fc4af1" }, { "dataPath": "params_shard_2.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": "de902d16c8f0fae8cf6809b45671dc1d" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 65667072, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128256, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65667072, "byteOffset": 0 } ], "md5sum": "eabfae79e5bcb138f608125f7c4973bd" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f6c8d2bfc6706e4d9a9365fed06cbbab" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d6452f82c6677e6d272f3c0817ab7149" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "0cb575c95faac7554663c46d45a258f0" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a3b8dace400c476f4e1a6b6d959d56dd" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "615b6cb0de1a51a03dde372cf670dd48" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "beb044ed479ddfc5e082e8aaf7966a3b" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "41c1c357b12a709017d421edf824029b" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6eba8aa39607e9b2bdcaebfce749a69d" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a642f9caa0cabe77efc7f800b85d380e" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 16384 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14696448 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14712832 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19955712 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24150016 } ], "md5sum": "02efb7aa842d19fc6a3d118325fd6fbe" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0749272dd444f67291fce0fefd9c5c28" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c87a9e1d4949dcb4dda94962428cbb9b" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "2aeaeb071c2a3a33e0013367eee1233c" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b8fe2528c4baf657777e75b7303c9b10" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9da20e11b4809b864f6a7f3a0d1dce26" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "842cb8f655199499fcf5e77229cf3b87" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3c5b55334917a31e9646d0e432fb4f69" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "586d217a9143c98187a7670af849cc58" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "df9beb53595be61b4dad6b23736e72be" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "19a8842c5d99029945f4ddedfc6ba167" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8ecf0e2662db80e0f02342ad556ef48d" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b1069c6d3883a2a5834b55d76961eb26" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "39f198fddf9fee5051b5f1ded6e8bb5d" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ff44b6460793ec2cedf1faa3e0fb1631" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "44d75f4f807dc2ddf2c1105d6fbd3b69" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "68182fa9c1b252183b06ab35acf1f9d9" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8a364445718d57b1a2569883d87c47c3" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "55858ebd0129e88fadcd3ba90ce695a4" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a9929ee5cb0811cd2bdb112b2adf132f" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "443a27f346aa8e694661a2055348da4a" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b5d504c77474954258f91f207de97f33" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8ab9b72ca2626c894460415a8d692a19" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 28360704, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 18907136 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24150016 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28344320 } ], "md5sum": "730fb67d6b77394962038004ccf2f3c8" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "33dbaa21a3e9278a546c7a71e84e0ae4" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "32e0af554a5b6214c3c98933244e2ef7" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3ae2be0ddd86f39ee109694d7c7f2197" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "19c5bd8e218d69f32a2efb843e97af71" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "8aa24a42b397b370f54d276218c1db83" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4c9df1002024a099aec122d942996e74" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "91284dbf91ba54faa3eef41c146e269f" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "676c21079a42f22ae561525655c70303" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "b35e4bd17999efeb19a16ee442c08651" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e8f8a8c55a8012c05e60157a7cc1a633" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "21e67b7999e86adff7a51969813a6647" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "48d9f620fd15cdf504b450d258a8b61f" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d2a0764be23f373d1b6158a638cb2bd2" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f2e50513a07aed348cb58f578d347669" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a1117b3fdd6be6178d2d831d80f78170" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a501687343155c8b56e0beb5b17f04bf" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0729df9d49f30453f467a93dd207ac93" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "1f6b4f2da13890c70e61dc38a9df4553" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "62049d55bbbeddf53f04c4fb2f8bddfd" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4f84205a208fc0bb993f2e9952e59880" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "040f151110d47abd5335ad2696a5c573" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "04dd5eb44e5ccb8c91b63e04c7172589" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "af9e5887338de7da48344f4a14ff79f8" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4c7a9e20621779f3193dc82b0694011b" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c4c854d62404d7c20ebdabe95dde9deb" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "77b83266fbb6b6859534ad7666b5dbee" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "647022b4cbac4f86070552fa874a1e12" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d5a81a5d5b50ebe56b8fd0c4b1391d68" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "45125f04fd506a457a0405af54d1eac0" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "a8347ce1c167b5da3153666a1399a729" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5531d6cffa1ff3c090f9f085e24bc768" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f5390bb29d24cf4175637accab8ef806" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c8b781745b6528416addc0db07360be7" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5b14fcd1d9463c1abe39eb4caeed089d" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "126f7b6fa83ed96808d36aaf556be5e5" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "580e2fa78dce56fbe0b63daf2155d033" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e39819c0fec42afa9500a73611a78ec0" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f290b4b8c184ba0a1cb46f560bf99d2c" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5ce31a28c139c75aa6183e8f5eb8bf73" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5b4c5df8cf8a4a84902bb213edf7e20b" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "49b240413f8500d1b0a81dcfdbc332c8" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3c8e0fe67b40aa4c46311c112f5285d6" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "e0d2b1c071f08ef865a8851e4605edb1" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "39d2b3ebe6a359b31d243aceabb2fb74" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "90e79dd9ff95bb88c3748056b598c214" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "301705521ed557441e6b2a0af4dae4ca" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "299f1e14a8ecea9a04359102fa2e1a78" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "166b34c12a1ecb57e58149dbe14f7f03" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "1f0c0fca6c511647a5dd2b092fadb13d" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b9ed6339a5dc0b039c3ff861270abc08" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c8fb596a627837edf81343081e505dd7" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "270aa6f8b83c7d0c97be9956754d7503" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "70fa1aac8a476757c67f99e14e0a7de9" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "76186f25ccb407d975f4193e79af1ee0" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a0363b19f11f2d80a17eaf8095033d44" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2a7b5207b75b55ea45884a789a6c5e2b" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d34e346febe9b1610f34aa25b790c691" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1ebece53e45cd60e7f8eb1ce1a08bb04" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "df08b9ca891dbd88bb0053c90aa815d1" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e9572cf0a6de362ad106a2469a50fa17" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "c768c7d8e7514599910fec945bc736ed" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a52eeb524135637b3c45fe6f74f5f171" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "011c7e9b4334eccbf515475541dea51a" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "29521281979afe42c04091d2ceab4826" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c8ae16d0353e1aa3703d0b6d8c4bcf80" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "3572eb3ca623678c6cfdfabff5245405" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "77171989f8afeabcbfa06a016a62b4fb" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4682cb6ff155ed4d9c4c597334cfe6ac" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8e16a2a74d424bc7abf9f25038678add" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c9b18ebb83cbabfb10c0d5d95f197269" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "204deba88f809a615c310d772b7ad2e0" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "970ce2455580a6fbccb322593601e9ce" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d3728fc4f1dbb142783eb8a286c3701d" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4bdd1a74fc9998991ffef9b58d9012a6" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "df5192e28b9638321f403c0ea9aed8f4" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9604348c4641658b1abd86d0fdd05fb4" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "89aa3fab15ac84ad902939199434792b" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "19fccdba6321eff5cba530acb9e74613" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "eb41c9d637a89aecb058562010d920e9" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5585d09d2871d9d309d624b1b0df8a8f" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6e322eef3d36820c807ae5cfa01cfe7b" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2713f2fb2ea86d1516719430b48ac607" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "27e09756d32324db5042aacf7a8b9da4" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "16203d286bba43735915fdd77972e573" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "300470ee4a406be940210f2cc5a102f5" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "cad89f3eb4858409ca0db01f5306223c" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e45d1114035332fcb1808076a79c0de5" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f2c9709c8bd1ec1467ec2b4b3e6355fb" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "16276ad15458ac486e19c6f086fbc805" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "636f9ef9efc25953775128ca086c818a" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "04344a8e176471a7cd7847c8581b7165" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e71a62656568f173165fab7ba61cbfb0" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "2fc3de69f7d8bc94e94818eb26e75d28" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4f9d2c6ad7efa61aea4862e427517609" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9ef235f7e243290c38afe68c24d40466" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "2a31d952b34c097321489e7010b23578" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "42a39259ca4bb3e7ba691ef03688687a" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "38d3a3dbbde7268601dd82aff76f1ef6" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "75910e1df1b9956c998d59fd6217ccd3" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "085c4e13b7181641d16ba14a20496b25" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "98f364ee91baaaf6360047a85985e7d3" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "2bc739639396c5cff85e202ada7b7377" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "98777228264a41a0910bd0fbba2c1046" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e419d511d4297e471194ec5e9f7869a3" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "57657e226713eb2173995b88e06adaa4" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "159575a809923fcf4f74f59ade2d16e0" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "fd19d17cd684c4856ed763d231e7e601" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "596abebc87cb19063bfa6f164eb6a92e" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7f0956188db260c2c5491fee98afb9af" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "766234c3af3ffd2b2e5d61235cb6941b" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "f6687acb1dbbb3c9ec661c9111bbb97c" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "987378ad8564faf25e7671c1ed61deeb" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f36b9ef04a3ad09dd83441b821291e60" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "a7ec8fc658494e75f0b2625944f250d1" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "895087de2eab1dca07ffd19840b088a1" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "634f231017d2a64ee3da0c292fab822f" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b6e5eb4ca0ea102219334599d32955a6" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bdbb53cb78c47670a3acf947c0a2c4b1" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6e6c9090c55d29c321ca64edfa9b104d" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "0e5e83d072785a8effc84658184bceed" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "764c1fb4549336e548de9bdede1e1a58" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ad29219533f33299b8d6e912539c5176" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "680d45ae8fbafb3034012fa083d3c9eb" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d57d6ff0ff69931568095cf8a716e027" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "51eabcfa4e39cd221a02ef2b19f94bf6" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a7335995cd6689417232a50098bd74b7" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "f10fe0bb6246745b2a7ee9b687bd216a" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "be5ddc95c321cd8b8f38765352fffdd7" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9a30f94b1c7a384a0c6aeff47f68ce2b" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "aa7b4b07f3600cdc2063246b93db1321" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "616381b9026f2e2bb43cb1514fa7084b" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "5ecabb7510edc303a2f47ed7ec1f493a" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "43a068bfeef762460558afe86543726e" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "520e30844acd9ab808f0008f27aaed4c" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "73769d3a7816d0324a2d5757c14ea6d8" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f999a407a397c9b65f028f6e5b0f69a2" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c3d3d1f82cf578c6df556e76c8a50730" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "9ac3e3b3d6f3d43764933694c480ffff" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c9d37acb596eb4d147c82ddfca967ef6" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b358bfce736a62f2925db40890f2a57f" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "56f0d6de2d6625e64b6a2d7ddbc5c648" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d8afa6c16baa6bdc6832b3662ff0a7dd" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c7a6d586c6188a3e461f6f64a6d53242" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3fd88d8feb78fbd8416d526a170e507f" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "900bed70e039eed12be44ab62dbb7abf" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f43073a6ca5d439cf83b025ba3057b08" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "7a08fb94f242f44b69cd5670716957d2" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ca5c10886dbe1b3e2debf8d72505b024" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9fd82c19d06731199cd4d0f977fbf31a" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "72d89e54cc3b7d3af16cfaa1eaaaf1e0" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "3be0c7d09efceefc04399fbf2cddf566" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b5bb016d88a10f5bec997a8f41cb12a5" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "064347708c649b583199196446758025" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3b06b3fb948c3469ad47ced4e6dacd9c" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6fd067351db23caa630baa09e324ab71" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "72fbdefd9f1ec39b9c50e750f5983f54" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "22845b28b8cb2d6a6e38edbc96d2a77f" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3bbae5549b49cbaaeecbf6589a05d1a1" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "82325f9ac7b2ea94c249ef7c11c29ab4" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c60a89e6297f103afb560413e08ec40a" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d6001fcc2de6a2f6a1e249e5db332ff9" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "9c61dd91aec2bcce80a0297683cca3e8" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "8ecadfd121e6f98f02aa60e845a6723f" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b78ca8b4f205fa2422b38a4383bbb996" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "58d66396a0926ce53608d357b14d2c79" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6ed718e1041f53b381d99384e3a63527" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "91ce28180b52d44707faf984f72fd977" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "33bb0e2469cb95cb78ebc3e4e4122080" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f9ecd521a2427810e8db5caf4820130b" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5fe11d9426d74ec331140e375989a219" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c9a887293de2a5205ead2c32c4e0e16c" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "51ba7455c3cf3970abdcc5c4d1fe1e7b" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9370fd855fe9e45fa884f1220cd80ac6" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "519248fd12edcf146d294de4edf752d7" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.40.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6485f31fc086ad31ae180abe8dce0e90" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c5b183ebc8ad7c68152138f0437854f3" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "a74392a2f44e571ff5faddcc73df9b3c" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f4309a00fe06cb738755f600a489046c" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6300dafb49985a9bdd7d64307c27c07c" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "bcd2a54d0569f72d09ae05a573a9b6f4" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "23ccad0b48d6b448a8b7ed36d85d9877" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "dcab10de26482f567a7b2d940ed13f7b" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "0b756daa1a208cb85ef29c2f772191e6" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8df8107e621f7e3b19b0022e8597d1a0" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2990050bbb08259310ee350c9c4ae8bd" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "cf905f8600432672aa6d0071dbccbf9b" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f055959d25a11ee8f4bb4f181bfabc41" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "3f6df1b0c9ca86f4d4484e9c7bf7112f" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9b660db99faddd0c1e8d728456b6f64b" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5236815ec11ebfaa2774aedcd3550f22" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6daa4ed0fd7b54da3f8fcfc761a38ad5" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "05c5fd7b31798c1a9f24718c4e8466a1" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "499552345462ebec0b0190f8bcc1cae4" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b08015b2e966c461b4306cc738378bd0" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "db7297a6c779d69add40db5d46d3a252" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "76d634d5bec1edbc5a794f57629a95e4" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "608f0e70bb5c4c4e4ceef83aa1115299" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a60d4b95d04bc0a6be6d97cc0d4ef735" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.41.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d6300d5d4c93399b2f6533875a93740e" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 29409280, "records": [ { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14696448 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 14712832 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29392896 } ], "md5sum": "f1cb92f2c0adda6ced872ea14cc2f941" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bd08191dc0effb865fa4220de2b809f5" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e2412b3d67eb2bc479c2df319206df00" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9ba869b02991de056ff90b3586a467d4" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "aef95a4bf6dd793cf406fd6b6abd2590" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.42.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "bbe8c3cfe3f51216c39449606949c123" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "057dea65d7a7fbfaee932b3903ef5127" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 9453568 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 }, { "name": "model.layers.42.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24150016 } ], "md5sum": "362e657a7341309821885188eb7d4226" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "8a61df6a0df1c8b923b9cf97e2cb90ef" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "df5df5e855bc02ec5e4fe38a51c9869a" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.43.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ad01e80ad1ad25fb41d7e4851173d17f" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8d90b02a3559430794d654cf6675e0f5" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "df3d6c7348b862d2297f77545ee8e3ce" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ee0effc76e9e0ddcf44719637f152e51" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 28360704, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 4194304 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 9437184 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13631488 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 13647872 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28327936 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28344320 } ], "md5sum": "d9c72172cb11c811bc63cef790a9d986" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "1e7768e76afd897370a9e32e3a522767" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "582ec74823d8669113e2fc3e2a15d900" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.44.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b11125bc07c738ea89cabb8254ff21e6" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7de81a4e774818aacf42d0282c314b36" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "853c4257fc4e2c7f20eae53987a8cc66" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.44.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "187fb57164765873667ddbf7af990056" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "21968b463a8f8a200254bfa18e059693" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e46df9e284aa56b5d8acd397a53b6a03" }, { "dataPath": "params_shard_259.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.45.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c417c05db51657da8a63eb352a5e3dac" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d90fae25bd02595a52f45f8fd4f182e7" }, { "dataPath": "params_shard_261.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.46.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4573ce373c7e67cb0081751a7eba481d" }, { "dataPath": "params_shard_262.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5121f6f2118019e7951de04e013154c5" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.45.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.46.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "7b6c285788187233d7c161c0708510dd" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6df9e6a017ec0e4da4409187d32f6791" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "fa73175ea13a5e7fd380d67a23a5c43d" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "1f52a5d58d118142c1f84bced285286f" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d73f6fa148346967e68cf90b0445fd3f" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "6a41fd6ff2dac3e1080a6b57e06eac23" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "462e173a3c80d4c629957a892c7ba421" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4c259e1d5379d0182f93b50a98025fbd" }, { "dataPath": "params_shard_271.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.47.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a3a07247bf9b417e440094edf007bedd" }, { "dataPath": "params_shard_272.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4f9278360a5a6af0e12809cf1bcc07a9" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ee7222675cff938a395ff28a17c3bef0" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.47.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "8dc53041ffdb127ee5c53f3c063a5a26" }, { "dataPath": "params_shard_275.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a69f39a56faedb5cf5614c2151d57b06" }, { "dataPath": "params_shard_276.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "95ae25d78c1e1632fe64ea0b2e145eb4" }, { "dataPath": "params_shard_277.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.48.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "940e994c489c4556fb1d4b1160a3f42b" }, { "dataPath": "params_shard_278.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f814691b5c1d89975f8ba6c1d3f7af31" }, { "dataPath": "params_shard_279.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.49.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1bf51229c28d0f40fcc34bb4978954d6" }, { "dataPath": "params_shard_280.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "a64addd692824f1fa68644237fe5a28a" }, { "dataPath": "params_shard_281.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.48.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.49.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "d803e5f2c188b030cdd002a954cee5df" }, { "dataPath": "params_shard_282.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "900dedcf56b3c527d85fb038049f66d5" }, { "dataPath": "params_shard_283.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f94d62d44291a2f815d1ffeb7e2dd507" }, { "dataPath": "params_shard_284.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8ed061f0f1a3cfce253a93f51d928916" }, { "dataPath": "params_shard_285.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "141b8bb456bd03106f29bc1af1cd280b" }, { "dataPath": "params_shard_286.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "cfe6e3f5ecebc7c35c916ff007ca0b52" }, { "dataPath": "params_shard_287.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e6e3a2b4ec12edb2798b4e5b83d9bd5d" }, { "dataPath": "params_shard_288.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "aab44e7437b25ebad441e16a69e75b05" }, { "dataPath": "params_shard_289.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.50.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "61e5561bb8b8ba6951d40b4fb29aed28" }, { "dataPath": "params_shard_290.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e5adc6158fc0e7ac878377a5de56174a" }, { "dataPath": "params_shard_291.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "91ce5d08db81c592bfcf62078f1bf896" }, { "dataPath": "params_shard_292.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.50.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "e61c964c3840e04f7af9f1e70cccdc79" }, { "dataPath": "params_shard_293.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d0210ab1139684462d6f33a1561da233" }, { "dataPath": "params_shard_294.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4aaf5bb877ec0aa95b56a382f39d3a15" }, { "dataPath": "params_shard_295.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.51.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "39e82e2c14795413cdf8e8c2fb3fe8c5" }, { "dataPath": "params_shard_296.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "931ed7e12d9485986acfe757af265126" }, { "dataPath": "params_shard_297.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "34398b1d510fc757b696fcde33918286" }, { "dataPath": "params_shard_298.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.51.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "3105a084a7eedf31b20d22ccfae7c62e" }, { "dataPath": "params_shard_299.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "243803fe5ed276bb7affe54ebc3d4a76" }, { "dataPath": "params_shard_300.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "843b03f976e65873f74f2f9680647b85" }, { "dataPath": "params_shard_301.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.52.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "51ff648dbce93330070a6c59a481bab6" }, { "dataPath": "params_shard_302.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0981f8e3ad3618984eafe00dd551f4b0" }, { "dataPath": "params_shard_303.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b3e4e660d9471060db1942e1d47b4c67" }, { "dataPath": "params_shard_304.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.52.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "db4334f1e008d2a4ad656458a3c0bd38" }, { "dataPath": "params_shard_305.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e87a4191f6c6ceb0f151b94d88ca9d18" }, { "dataPath": "params_shard_306.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "65bc5a93951cd78c95d8b54992f7d3fe" }, { "dataPath": "params_shard_307.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.53.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "209cea538a6baf7eda3eca35ebca145c" }, { "dataPath": "params_shard_308.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a4d3f1de8ca8e4147bd85a0a98baf1ae" }, { "dataPath": "params_shard_309.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9d4d1d75d925d3366ded8ceaaaa38a82" }, { "dataPath": "params_shard_310.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f98959c5b4326b788828309d20565720" }, { "dataPath": "params_shard_311.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.54.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3508a911901adeb913249ed929f92cdc" }, { "dataPath": "params_shard_312.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "654671beb55bb499beceba490a4553e7" }, { "dataPath": "params_shard_313.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.53.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.54.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "977c2077746ce3845a97a8d2a1bb122b" }, { "dataPath": "params_shard_314.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d4a4faa568704dcfcd1250cf05d317f6" }, { "dataPath": "params_shard_315.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4dac44d55bf27b5ac8784dbdee388566" }, { "dataPath": "params_shard_316.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "76d8869cc419e3490bd632e7d2f9580f" }, { "dataPath": "params_shard_317.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bda85cb132cc16d760442179b4c4e3a0" }, { "dataPath": "params_shard_318.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "94c72cdc3ba3d2100816fc9694f9b5b4" }, { "dataPath": "params_shard_319.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.55.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cecb841defda1904d279685d9dd1692f" }, { "dataPath": "params_shard_320.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e8ec99266ea6310bde33a07d24ff040a" }, { "dataPath": "params_shard_321.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b8465b9014b08fcbb975194bfe28da4a" }, { "dataPath": "params_shard_322.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.55.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "ef8e0049bacf003652a2ed7a5fb6e34c" }, { "dataPath": "params_shard_323.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f4c04699fc2e7c27bc17e294ebbd2539" }, { "dataPath": "params_shard_324.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "14bfe186d83087cd1bc3343485ef377d" }, { "dataPath": "params_shard_325.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.56.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "062890656b11f0d99fc83bfa877e3e44" }, { "dataPath": "params_shard_326.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c6979bf037a8439b22fe096306d7806f" }, { "dataPath": "params_shard_327.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "438eb5ea50578fd1c7d24a6be6b557c6" }, { "dataPath": "params_shard_328.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "83c6ab6979f1ff24255a7ec1608f8147" }, { "dataPath": "params_shard_329.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.57.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "507419b23089832287f0d5286b98c3c4" }, { "dataPath": "params_shard_330.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6e91087fa69410a0c3b7c7bd1200be25" }, { "dataPath": "params_shard_331.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.56.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.57.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "71dd92af68ef4cf5abd179c3572c1a6a" }, { "dataPath": "params_shard_332.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6abcd357b44bbbc505e1538c97160a75" }, { "dataPath": "params_shard_333.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4dd96306faca8d7b4102b1102cc3ec05" }, { "dataPath": "params_shard_334.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "21a88d0caea341fe487d1c5c3dd4cb58" }, { "dataPath": "params_shard_335.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "994253f7ef500626d6c682ca4d1d08c9" }, { "dataPath": "params_shard_336.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9fe052aef17272cd7cb5d43d39a1452a" }, { "dataPath": "params_shard_337.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.58.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b803c047f6a10db0a14f0b12a9c2956d" }, { "dataPath": "params_shard_338.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "87c7a695176f01029f6200f69a7b31c8" }, { "dataPath": "params_shard_339.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b7146269301a14a029ddc3cfd09e7eaf" }, { "dataPath": "params_shard_340.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.58.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "54d8e180fd73755a9cf4b13a9e827077" }, { "dataPath": "params_shard_341.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a8252c3fadcf01b7ba73908551c6fdd9" }, { "dataPath": "params_shard_342.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8ae560152ef6935fd2afcd7ff4e9d85f" }, { "dataPath": "params_shard_343.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.59.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c68728710a1263f0a26e260cdaafb452" }, { "dataPath": "params_shard_344.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1a7483bf87bfbc07b583e9e9608e8319" }, { "dataPath": "params_shard_345.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.60.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "abb2b1988a906e25fd90ec20ac1d011f" }, { "dataPath": "params_shard_346.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "449cafadba6827b58562d6e4a2dff60e" }, { "dataPath": "params_shard_347.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.59.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.60.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "cea65a908366a15771483c977f7a7d32" }, { "dataPath": "params_shard_348.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8092ce818cb2b1a61b362db71c9276b2" }, { "dataPath": "params_shard_349.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ae43969c9df1d2b65de75a4e8c0b63bf" }, { "dataPath": "params_shard_350.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5155541f8d6114aa707fdddd9bbfff5d" }, { "dataPath": "params_shard_351.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3eb7043ff5dec9c49e8705a615e326b0" }, { "dataPath": "params_shard_352.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "ce9483dbcca7c0cce478fe599cd67290" }, { "dataPath": "params_shard_353.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "66ba5ff467a5f2abab436fef2624a028" }, { "dataPath": "params_shard_354.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "32685671227e75b883caf8db42d4f343" }, { "dataPath": "params_shard_355.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.61.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d95701b10497b195dd03e10d77315a7f" }, { "dataPath": "params_shard_356.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "eca9e93addf13aaedb5ec00462063017" }, { "dataPath": "params_shard_357.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3368dea5400e9cdeded8bc2350bfed39" }, { "dataPath": "params_shard_358.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.61.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "8800520280af6b811b8b21b1b092bae0" }, { "dataPath": "params_shard_359.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "545f8a74c29f279b6d3f6a5431e5de1f" }, { "dataPath": "params_shard_360.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5b6c6d772038b37b3f40f9dae9a34464" }, { "dataPath": "params_shard_361.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.62.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "614668da99314dd6aba21c297633edb7" }, { "dataPath": "params_shard_362.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "aae1bdd6f7ea161f527490efd0f7ee47" }, { "dataPath": "params_shard_363.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.63.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3b71117f9eb195fb505836139feb281d" }, { "dataPath": "params_shard_364.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6b9ccba7369fad4510affd4bc9b08c7b" }, { "dataPath": "params_shard_365.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.62.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.63.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "4c1fc9720f9e306e09a91977102d40b2" }, { "dataPath": "params_shard_366.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ea3f305a1f5c7db4394319a999c8a3e6" }, { "dataPath": "params_shard_367.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f35e8cd10beb8d5429e160af4029b307" }, { "dataPath": "params_shard_368.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0ea03e34c72b3af8b58f00293bb9b9a0" }, { "dataPath": "params_shard_369.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.64.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "961fda5f39c742d98819434c01e5b974" }, { "dataPath": "params_shard_370.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.64.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "9baa6e1225d57e92789a227a14b775c0" }, { "dataPath": "params_shard_371.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7873afd88f8991e2a386db7d24c27ee2" }, { "dataPath": "params_shard_372.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "776dcdf468d46fce6115c4181c1a0507" }, { "dataPath": "params_shard_373.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.64.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "54bb40285b0a7a64417ba5d66dcf0353" }, { "dataPath": "params_shard_374.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.64.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "deca20af9148357a69c6326e329d0fe7" }, { "dataPath": "params_shard_375.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.65.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "00d4a8d0c8c68efdcac0905aa264c32b" }, { "dataPath": "params_shard_376.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.64.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.64.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.64.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.64.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.65.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "93cea6c6ea09f5e702906b8233442474" }, { "dataPath": "params_shard_377.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bd1636dfb215170770bd8c27c237ad1e" }, { "dataPath": "params_shard_378.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "d9839ab6d0fc55ee554403bff926af50" }, { "dataPath": "params_shard_379.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.65.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7c73d263cf74508a0bcf889baa58408f" }, { "dataPath": "params_shard_380.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.65.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5f137b9983eaab4cb8ef33319c07bd8d" }, { "dataPath": "params_shard_381.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.66.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ef3c1e54d837125a77ad9bb901d43b69" }, { "dataPath": "params_shard_382.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.65.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.65.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.65.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.65.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.66.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "2ea1f83b38fbc4bd3b7748daed8d8b0d" }, { "dataPath": "params_shard_383.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "33c6e7ee924697b41e4b1122f7919100" }, { "dataPath": "params_shard_384.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9af0b126bef70938b3c2c4929ab155d5" }, { "dataPath": "params_shard_385.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.66.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "bc6abb8a80d7ea26f0f370180fbab515" }, { "dataPath": "params_shard_386.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.66.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0f4ba4ab96d8b2e30c04f519e44b7dd9" }, { "dataPath": "params_shard_387.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.67.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ad94e07270fe86bec9e683c298e63d66" }, { "dataPath": "params_shard_388.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.66.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.66.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.66.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.66.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.67.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "1864b067b32e87603b62b610c8eac8c6" }, { "dataPath": "params_shard_389.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d546fb33c7380fb25d3c2ed1d433a12a" }, { "dataPath": "params_shard_390.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "d9114e7977807084c7a30e22b5457265" }, { "dataPath": "params_shard_391.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.67.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "704539f2f468cb83913a503bf355a1c9" }, { "dataPath": "params_shard_392.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.67.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e664fc84ab9ee3dafde7bae4652ab32b" }, { "dataPath": "params_shard_393.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "756c271e5b4fcadfcf43b9e025c3cacc" }, { "dataPath": "params_shard_394.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3edd9f543d9b166779b6ca7d9c02262f" }, { "dataPath": "params_shard_395.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.68.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "dcdf260af629d4f75dcb888a0fdfbc88" }, { "dataPath": "params_shard_396.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "be7af4e995d2d14ee97f9ebd069fd98e" }, { "dataPath": "params_shard_397.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.67.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.67.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.67.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.67.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.68.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "b88a52aef92cb9db66d33a5ef1653f7b" }, { "dataPath": "params_shard_398.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.68.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "023a80d54971e6565c15ae74d0ccb402" }, { "dataPath": "params_shard_399.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.69.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4031c373bbf5ecdc6053af246fded7b3" }, { "dataPath": "params_shard_400.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.68.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.68.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.68.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.69.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "6eb9d36e9f2e4f6f1075c9531160f14c" }, { "dataPath": "params_shard_401.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9dff8be974ca6032aed2e039749ac7b0" }, { "dataPath": "params_shard_402.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ae9bf2efe0879bf58b559d7b7d158320" }, { "dataPath": "params_shard_403.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.69.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "dba8e16727ac5964691235c94578a1a1" }, { "dataPath": "params_shard_404.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.69.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a643e085ace05ac29e51e216bb0ba5b4" }, { "dataPath": "params_shard_405.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.70.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2768a4849cecdbdde7efcac958ef4a0f" }, { "dataPath": "params_shard_406.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.69.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.69.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.69.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.69.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.70.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "443f696fb724d2342f5e456c8fd71aaf" }, { "dataPath": "params_shard_407.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "39f0067ef63006a5707f404929302c3c" }, { "dataPath": "params_shard_408.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3329f5bc1f21ffb216d45ab44765581a" }, { "dataPath": "params_shard_409.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.70.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a0cba5c9218a46a49fd870db053afb74" }, { "dataPath": "params_shard_410.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.70.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fbe8250c162b614085b50350a97f4361" }, { "dataPath": "params_shard_411.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "cafc548123d9a6f95de80e3296b243cc" }, { "dataPath": "params_shard_412.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "d43de002a99e904c031902b4db879fef" }, { "dataPath": "params_shard_413.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.71.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3405e30947f32c214a747e918e9ce616" }, { "dataPath": "params_shard_414.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "598bf9c23b8696ecccce5591fb36e4a9" }, { "dataPath": "params_shard_415.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.70.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.70.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.70.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.70.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.71.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "586810e252ebff787ec047600a49b91b" }, { "dataPath": "params_shard_416.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "62a0797e872ff0c3590637f7836d05db" }, { "dataPath": "params_shard_417.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e382240ac846208d78af000efafb5f96" }, { "dataPath": "params_shard_418.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5c0eeff47c1c97c54ca4c05ccd985ff7" }, { "dataPath": "params_shard_419.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "21dc7feacf87851367a05de35b5ba148" }, { "dataPath": "params_shard_420.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3320ac800c057810c3c6cdf2d79a76ef" }, { "dataPath": "params_shard_421.bin", "format": "raw-shard", "nbytes": 23117824, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 18907136 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 } ], "md5sum": "8b918fe28a09192db1bbfc6d234e29cf" }, { "dataPath": "params_shard_422.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "73b6a303c04e423fb1880249a5f1ffdb" }, { "dataPath": "params_shard_423.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "dcdcd9aff2a581ef66bddc2248edc8e9" }, { "dataPath": "params_shard_424.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e265c6b5620e82a07267b19d021561c2" }, { "dataPath": "params_shard_425.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "03519af6062472a3296f1b3b6852de31" }, { "dataPath": "params_shard_426.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "aef442217ebb2c1ca1d920c868b6bf58" }, { "dataPath": "params_shard_427.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "9ad3b8af7ce22491cf917615ce5a4f9f" }, { "dataPath": "params_shard_428.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b6f72bd962f1139b5ecf5f7df4006610" }, { "dataPath": "params_shard_429.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "dd77c7dc9cd9b88f45dda1294ab86be5" }, { "dataPath": "params_shard_430.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b901db7e83c4ec06ebf6df67fb2935ff" }, { "dataPath": "params_shard_431.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "15b06bb15185c5377cb52a269cb2f607" }, { "dataPath": "params_shard_432.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.71.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e47c979f8323b59ca45b004b3e149cd3" }, { "dataPath": "params_shard_433.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.71.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "5ef809160fcc43406d9c88f50c7c8619" }, { "dataPath": "params_shard_434.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.72.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0c5d3e4b052788815a80ba610743bd63" }, { "dataPath": "params_shard_435.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "be20eeac0075c8ba2b6eb601f8dd58e1" }, { "dataPath": "params_shard_436.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "decf54dc18676fd8053098d5a5fe53e1" }, { "dataPath": "params_shard_437.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.72.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5f1c0c8b5963fb770482d129501f336f" }, { "dataPath": "params_shard_438.bin", "format": "raw-shard", "nbytes": 29409280, "records": [ { "name": "model.layers.71.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.71.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.72.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14696448 }, { "name": "model.layers.72.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 14712832 }, { "name": "model.layers.72.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29392896 } ], "md5sum": "59b448618d76642c5be68fa7d9188485" }, { "dataPath": "params_shard_439.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.72.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6c07558957355975b74a225fc78652c0" }, { "dataPath": "params_shard_440.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.73.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6b9d0389322144d65f1bd54b8a1c69b0" }, { "dataPath": "params_shard_441.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c20feb5d90329261a1ea0fc9576178eb" }, { "dataPath": "params_shard_442.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "6081ae1b7f4f99f5d0d19e34c25640f4" }, { "dataPath": "params_shard_443.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.73.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "9b4d7a04e3840a9f7284347ef3b96aab" }, { "dataPath": "params_shard_444.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.73.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "62c3a6b781ead372ca66abd7648210cc" }, { "dataPath": "params_shard_445.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.72.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.72.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.73.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.73.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 9453568 }, { "name": "model.layers.73.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 }, { "name": "model.layers.73.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24150016 } ], "md5sum": "f9d502b4bbcc6974ddfaa387c11b38c4" }, { "dataPath": "params_shard_446.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.74.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "12dd034e81beaff286e5eb4128741920" }, { "dataPath": "params_shard_447.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.74.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4810b4188ef168940bd90db55a4c1c07" }, { "dataPath": "params_shard_448.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.74.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4e0081820245793d572636ea94c26e47" }, { "dataPath": "params_shard_449.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "0fde6ddff285db0b571b392add47b289" }, { "dataPath": "params_shard_450.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f31d3226a289c1d7343d3c81d83b82e3" }, { "dataPath": "params_shard_451.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.75.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "75f07a69d7acec59bb2d14a082b6a0c3" }, { "dataPath": "params_shard_452.bin", "format": "raw-shard", "nbytes": 28360704, "records": [ { "name": "model.layers.73.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.74.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 4194304 }, { "name": "model.layers.74.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 9437184 }, { "name": "model.layers.74.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13631488 }, { "name": "model.layers.74.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 13647872 }, { "name": "model.layers.74.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28327936 }, { "name": "model.layers.75.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28344320 } ], "md5sum": "efdcf7bf69f500d30e237b9debf66018" }, { "dataPath": "params_shard_453.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "19bc103f69d7c3d3a6d77b3f6d3cb772" }, { "dataPath": "params_shard_454.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f853d0d67954ee6c4000b711158231ac" }, { "dataPath": "params_shard_455.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.75.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5b1eacdb88302f9816956a4438752fda" }, { "dataPath": "params_shard_456.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.75.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "24aeaae829308a24f7088fd30eaafa23" }, { "dataPath": "params_shard_457.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.76.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3d2f7ccd467832cdf35d9ae04a5b2a21" }, { "dataPath": "params_shard_458.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.75.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.75.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.75.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.75.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.76.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "b481e0ac24f4b3430c5127ff6998dd23" }, { "dataPath": "params_shard_459.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "edb7409b501ee45556a29d691237a3d1" }, { "dataPath": "params_shard_460.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "43544a50a4522b627f1faf915b196674" }, { "dataPath": "params_shard_461.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.76.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "73e2eb05bfe747d1f528c715d1f5ee32" }, { "dataPath": "params_shard_462.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.76.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a2c08d361a56a1f8e6aa9c1c71b6411a" }, { "dataPath": "params_shard_463.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.77.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c34fd388358cabd8f6793e6d82071cfa" }, { "dataPath": "params_shard_464.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.77.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "246aab455b595f0b2d33d41b157e5d9b" }, { "dataPath": "params_shard_465.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.76.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.76.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.76.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.76.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.77.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.77.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "2359aa77de88c93940dc23f74cdef9e7" }, { "dataPath": "params_shard_466.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "4ac6f0eef3dffb187c5f1b1e7502096f" }, { "dataPath": "params_shard_467.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5905a0f81f856e0f200140784b57ceaa" }, { "dataPath": "params_shard_468.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.77.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "149a33919a28bbada037e26394f2d6bd" }, { "dataPath": "params_shard_469.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.78.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b2e800a4c2c588da8cc3ba481803d548" }, { "dataPath": "params_shard_470.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.77.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.77.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.77.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.78.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "d6a05ae6fdfc65baadddbc4df9fd61a5" }, { "dataPath": "params_shard_471.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b62f59439eb159d4075cd75127749901" }, { "dataPath": "params_shard_472.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "0b460baf1366fb6bdc13d0e16e794b2c" }, { "dataPath": "params_shard_473.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.78.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e5149ddf9010dce6552d7cfca108f8e4" }, { "dataPath": "params_shard_474.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.78.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c0d73d0dda317ffbc00f5a60dcd07559" }, { "dataPath": "params_shard_475.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.79.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e0124157be6b65b37063e5c6ad818bad" }, { "dataPath": "params_shard_476.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.78.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.78.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.78.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.78.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.79.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "c51865c6341b8a04d55e8dc7cb93b0d2" }, { "dataPath": "params_shard_477.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "529e087dcb072ba0ff7d58659deb5ad1" }, { "dataPath": "params_shard_478.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "41ec32d0eaf39eb787ed88509d920477" }, { "dataPath": "params_shard_479.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.79.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1b7dd562570b6780d686dc1e26d4b57d" }, { "dataPath": "params_shard_480.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.79.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "522ae970ab1f5874b39775fba83bfe59" }, { "dataPath": "params_shard_481.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.79.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.79.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.79.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.79.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.norm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "a2a4007bb311b0abbfe83c792a6c46d3" } ] }