{ "metadata": { "ParamSize": 311, "ParamBytes": 965310464.0, "BitsPerParam": 5.002534272041053 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 116686848, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 116686848, "byteOffset": 0 } ], "md5sum": "8496ee5c3f41496d18140cd635943654" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 22330368, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14585856, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 14585856 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 14588928 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 21470208 } ], "md5sum": "bb0a5bd2928a3440a383c16112df04d1" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "f165dd0ff289221e28ef26d0dde6af71" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "de3714adb12904b9e7e78bcf2f5cba8b" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "0489015ee88c3935db3c1e974912a2ac" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "afb0d87a160317f7a177730959e3778b" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "f988690f5c5d2aef563f20e5e1115e20" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "c5219a786e502bcc59835195f98a1ddd" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "c02a506a18a5fbd8cdb4a70999bb7c57" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "6b53dc9c6cb0f95b4247bebb2f9ae143" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "2bee577420e3a6688ae3acaaf88fa818" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "ff8bc7d3b56a3b210a1bbc8e2c59a551" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "2f383afc6ee86eacf9017dc78612e5c8" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "3e2a07a821b1dcb36d22ea02f2220599" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "c80b73bd5c3089974df9e684d1d17e3f" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "7b77a31382d1381d3fe8f489dd0941b2" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "22dad11180031dd6bf808ea7997e38d8" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "785929af8a3c3112a3e92cf3b0c714c2" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "2d68ac7ba9a17b81cb585534c6b2ea02" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "60330d09fee856364b236ee56ff09bd0" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "ec018fa4fcc3f2e97cb3d328601f4d57" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "e884a0e32db4c111f087940c0c3561ba" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "c97e767e0f274dcfba572b90ff887494" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "a04767d48dbff699900ddd0f2175456a" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "a182ace09b771a0d81dba7b399c6fb8f" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "04022209b57e9f71532affef122f32e9" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "b2cf9f6e3c4566b0fc774c2e7d4fc48c" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "745941fab8d83b78aa9c3158af1c044a" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "f4787352f47bc1ee9a565abe80defe0d" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 18589696, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.norm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 } ], "md5sum": "25edd595bb3a1a00de8a48f28b9a7c67" } ] }