| { |
| "metadata": { |
| "ParamSize": 269, |
| "ParamBytes": 1033572352.0, |
| "BitsPerParam": 4.501551474039708 |
| }, |
| "records": [ |
| { |
| "dataPath": "params_shard_0.bin", |
| "format": "raw-shard", |
| "nbytes": 155582464, |
| "records": [ |
| { |
| "name": "lm_head.q_weight", |
| "shape": [ |
| 151936, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 155582464, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "72cb3eafbe18817cad348f5ee66837bc" |
| }, |
| { |
| "dataPath": "params_shard_1.bin", |
| "format": "raw-shard", |
| "nbytes": 155582464, |
| "records": [ |
| { |
| "name": "model.embed_tokens.q_weight", |
| "shape": [ |
| 151936, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 155582464, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "54f5be3c632676377895e11452dc6179" |
| }, |
| { |
| "dataPath": "params_shard_2.bin", |
| "format": "raw-shard", |
| "nbytes": 19447808, |
| "records": [ |
| { |
| "name": "model.embed_tokens.q_scale", |
| "shape": [ |
| 151936, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 19447808, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "28c847cf8730bcb091006ab518a6821d" |
| }, |
| { |
| "dataPath": "params_shard_3.bin", |
| "format": "raw-shard", |
| "nbytes": 25792512, |
| "records": [ |
| { |
| "name": "lm_head.q_scale", |
| "shape": [ |
| 151936, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 19447808, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.0.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 19447808 |
| }, |
| { |
| "name": "model.layers.0.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 19451904 |
| }, |
| { |
| "name": "model.layers.0.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 25088000 |
| } |
| ], |
| "md5sum": "e00a0634d0d5ac4d91b66ca74a00337b" |
| }, |
| { |
| "dataPath": "params_shard_4.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.0.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.0.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.0.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.0.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.0.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.0.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.0.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.0.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.1.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.1.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.1.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "ad0bf82f94777f6d48d49dd3f0fa87a1" |
| }, |
| { |
| "dataPath": "params_shard_5.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.1.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.1.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.1.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.1.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.1.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.1.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.1.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.1.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.10.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.10.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.10.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "31d9f2bba7ba8ef4a3ea777b15f524dc" |
| }, |
| { |
| "dataPath": "params_shard_6.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.10.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.10.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.10.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.10.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.10.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.10.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.11.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.11.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.11.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "645b0cc2b5b3f544dc5f040f4294d45e" |
| }, |
| { |
| "dataPath": "params_shard_7.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.11.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.11.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.11.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.11.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.11.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.11.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.11.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.11.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.12.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.12.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.12.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "b50dd8500609fe269d6f0120c1528c29" |
| }, |
| { |
| "dataPath": "params_shard_8.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.12.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.12.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.12.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.12.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.12.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.12.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.12.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.12.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.13.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.13.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.13.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "9ced87de2131e31be0a0737f2af8251d" |
| }, |
| { |
| "dataPath": "params_shard_9.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.13.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.13.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.13.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.13.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.13.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.13.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.13.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.13.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.14.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.14.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.14.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "ee9d4fa398d3cb578dabec6731f1450b" |
| }, |
| { |
| "dataPath": "params_shard_10.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.14.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.14.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.14.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.14.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.14.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.14.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.14.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.14.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.15.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.15.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.15.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "20a89d4119a9764893447e6e229dd040" |
| }, |
| { |
| "dataPath": "params_shard_11.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.15.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.15.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.15.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.15.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.15.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.15.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.15.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.15.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.16.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.16.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.16.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "3740799cd01061fbfc2dff5f12ed719d" |
| }, |
| { |
| "dataPath": "params_shard_12.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.16.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.16.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.16.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.16.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.16.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.16.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.16.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.16.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.17.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.17.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.17.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "cac98ea07f29e5982cda8a28599567f4" |
| }, |
| { |
| "dataPath": "params_shard_13.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.17.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.17.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.17.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.17.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.17.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.17.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.17.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.17.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.18.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.18.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.18.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "b3bb4c955f71dee6608fc486aaa61278" |
| }, |
| { |
| "dataPath": "params_shard_14.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.18.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.18.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.18.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.18.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.18.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.18.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.18.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.18.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.19.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.19.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.19.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "9dff11a95ad204172f2235f3c5e76802" |
| }, |
| { |
| "dataPath": "params_shard_15.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.19.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.19.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.19.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.19.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.19.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.19.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.19.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.19.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.2.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.2.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.2.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "4645a8dd0ee95c06af543c44852c8959" |
| }, |
| { |
| "dataPath": "params_shard_16.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.2.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.2.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.2.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.2.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.2.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.2.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.20.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.20.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.20.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "42f556367bbc8219ae39204d16da7766" |
| }, |
| { |
| "dataPath": "params_shard_17.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.20.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.20.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.20.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.20.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.20.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.20.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.21.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.21.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.21.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "7dab31580bd17dd65c1cda3f85e35b9f" |
| }, |
| { |
| "dataPath": "params_shard_18.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.21.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.21.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.21.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.21.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.21.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.21.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.21.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.21.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.22.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.22.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.22.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "07141be27224c9796025f2b0eb2ca62a" |
| }, |
| { |
| "dataPath": "params_shard_19.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.22.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.22.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.22.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.22.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.22.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.22.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.23.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.23.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.23.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "46e05e1d31bc704e9f4424bcf8338a0a" |
| }, |
| { |
| "dataPath": "params_shard_20.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.23.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.23.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.23.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.23.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.23.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.23.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.23.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.23.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.3.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.3.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.3.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "108dc6d365e4ab79534a54a6be17fe9a" |
| }, |
| { |
| "dataPath": "params_shard_21.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.3.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.3.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.3.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.3.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.3.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.3.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.4.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.4.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.4.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "80d681c512be8bdbb2182eaac7e6d098" |
| }, |
| { |
| "dataPath": "params_shard_22.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.4.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.4.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.4.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.4.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.4.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.4.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.5.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.5.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.5.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "9c0ffc70bc19f05240deb1efe39f5e6f" |
| }, |
| { |
| "dataPath": "params_shard_23.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.5.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.5.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.5.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.5.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.5.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.5.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.6.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.6.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.6.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "f6fd0065602c4aa1c5827ef6b3255f9c" |
| }, |
| { |
| "dataPath": "params_shard_24.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.6.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.6.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.6.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.6.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.6.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.6.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.7.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.7.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.7.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "5a3cce711dfc6ab1d3b42f9e6488977e" |
| }, |
| { |
| "dataPath": "params_shard_25.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.7.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.7.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.7.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.7.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.7.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.7.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.8.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.8.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.8.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "2213c3475bf330c42da5ca6a45ce78cb" |
| }, |
| { |
| "dataPath": "params_shard_26.bin", |
| "format": "raw-shard", |
| "nbytes": 28479488, |
| "records": [ |
| { |
| "name": "model.layers.8.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.8.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.8.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.8.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.8.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.8.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.8.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.8.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.9.input_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| }, |
| { |
| "name": "model.layers.9.mlp.down_proj.q_weight", |
| "shape": [ |
| 2048, |
| 688 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 5636096, |
| "byteOffset": 22138880 |
| }, |
| { |
| "name": "model.layers.9.mlp.down_proj.q_scale", |
| "shape": [ |
| 2048, |
| 172 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 704512, |
| "byteOffset": 27774976 |
| } |
| ], |
| "md5sum": "33bb46d7c8a693ddd2626d45888a7984" |
| }, |
| { |
| "dataPath": "params_shard_27.bin", |
| "format": "raw-shard", |
| "nbytes": 22138880, |
| "records": [ |
| { |
| "name": "model.layers.9.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 11008, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 11272192, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.9.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 11008, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1409024, |
| "byteOffset": 11272192 |
| }, |
| { |
| "name": "model.layers.9.post_attention_layernorm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 12681216 |
| }, |
| { |
| "name": "model.layers.9.self_attn.c_attn.bias", |
| "shape": [ |
| 6144 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 12288, |
| "byteOffset": 12685312 |
| }, |
| { |
| "name": "model.layers.9.self_attn.c_attn.q_weight", |
| "shape": [ |
| 6144, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6291456, |
| "byteOffset": 12697600 |
| }, |
| { |
| "name": "model.layers.9.self_attn.c_attn.q_scale", |
| "shape": [ |
| 6144, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 786432, |
| "byteOffset": 18989056 |
| }, |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_weight", |
| "shape": [ |
| 2048, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 2097152, |
| "byteOffset": 19775488 |
| }, |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_scale", |
| "shape": [ |
| 2048, |
| 64 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 262144, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.norm.weight", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 22134784 |
| } |
| ], |
| "md5sum": "3f31ba1f3d52eb75690d1f1698c46a40" |
| } |
| ] |
| } |
