| { |
| "metadata": { |
| "ParamSize": 885, |
| "ParamBytes": 68971290624.0, |
| "BitsPerParam": 4.500203998122676 |
| }, |
| "records": [ |
| { |
| "dataPath": "params_shard_0.bin", |
| "format": "raw-shard", |
| "nbytes": 201326592, |
| "records": [ |
| { |
| "name": "lm_head.q_weight", |
| "shape": [ |
| 32768, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 201326592, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "db9f19df9a3fde357d6d4feef9fe3259" |
| }, |
| { |
| "dataPath": "params_shard_1.bin", |
| "format": "raw-shard", |
| "nbytes": 201326592, |
| "records": [ |
| { |
| "name": "model.embed_tokens.q_weight", |
| "shape": [ |
| 32768, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 201326592, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4730bf413155f7cff0bbe7c65ae7f91d" |
| }, |
| { |
| "dataPath": "params_shard_2.bin", |
| "format": "raw-shard", |
| "nbytes": 25165824, |
| "records": [ |
| { |
| "name": "model.embed_tokens.q_scale", |
| "shape": [ |
| 32768, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 25165824, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6799bcc4180681747367f4a21d1dc202" |
| }, |
| { |
| "dataPath": "params_shard_3.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.0.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fe7aaf8e967e11603e5acc4deea46df7" |
| }, |
| { |
| "dataPath": "params_shard_4.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.0.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "dd8a23708bce94d260efdb802b005333" |
| }, |
| { |
| "dataPath": "params_shard_5.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.0.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fefc6aede3f0c54f2692ef359ee9b76b" |
| }, |
| { |
| "dataPath": "params_shard_6.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.0.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d584859fad5936585fb81d7dcce5bd66" |
| }, |
| { |
| "dataPath": "params_shard_7.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.0.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f1f93fd5b9c0194ef8cb584ed38d6b1b" |
| }, |
| { |
| "dataPath": "params_shard_8.bin", |
| "format": "raw-shard", |
| "nbytes": 25214976, |
| "records": [ |
| { |
| "name": "lm_head.q_scale", |
| "shape": [ |
| 32768, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 25165824, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.0.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 25165824 |
| }, |
| { |
| "name": "model.layers.0.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 25190400 |
| } |
| ], |
| "md5sum": "43d258bb3c41e0faf770e4b70ac811c1" |
| }, |
| { |
| "dataPath": "params_shard_9.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.0.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a5ade5a8b88fcbd5006337d2344ff1c1" |
| }, |
| { |
| "dataPath": "params_shard_10.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.1.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2ca68f40a0c608fcda84834f730ebbe3" |
| }, |
| { |
| "dataPath": "params_shard_11.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.1.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "eaf17c64dc949c9fbb165768283add90" |
| }, |
| { |
| "dataPath": "params_shard_12.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.1.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b96f34be676e926866762f259a29b9af" |
| }, |
| { |
| "dataPath": "params_shard_13.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.1.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "312c12dced1ee0fd809411d9810c0dcb" |
| }, |
| { |
| "dataPath": "params_shard_14.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.1.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0ba783c6918f5789014cd4434b4f5808" |
| }, |
| { |
| "dataPath": "params_shard_15.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.1.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f7d177818024bf11e009a2c72879155b" |
| }, |
| { |
| "dataPath": "params_shard_16.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.0.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.0.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.1.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.1.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.1.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "480a460c814f2ae83f5eae60284427f0" |
| }, |
| { |
| "dataPath": "params_shard_17.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.10.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "40155f5c633e88509937a774fd7a4c96" |
| }, |
| { |
| "dataPath": "params_shard_18.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.10.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ecb39e85bcdabca48d6dc677cfe99206" |
| }, |
| { |
| "dataPath": "params_shard_19.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.10.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "72ab552bd08ed96839a9fe6fb56a43fb" |
| }, |
| { |
| "dataPath": "params_shard_20.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.10.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "39b6da58eca7fb33a21c60bb278614a4" |
| }, |
| { |
| "dataPath": "params_shard_21.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.1.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.10.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.10.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.10.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "a4203c42348400ccf143825ff32498f6" |
| }, |
| { |
| "dataPath": "params_shard_22.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "aa0b316b0fb7a65b85abef979c56c1af" |
| }, |
| { |
| "dataPath": "params_shard_23.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.11.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ad601d7a1090288b97ed5012397a5de2" |
| }, |
| { |
| "dataPath": "params_shard_24.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.11.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "52aa773827e696db162c7b688fc5fe73" |
| }, |
| { |
| "dataPath": "params_shard_25.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.11.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d77a735b31dd9ca7a377bfa9d6b8dbfb" |
| }, |
| { |
| "dataPath": "params_shard_26.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.11.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e969ea4b7935aec10e221831865c8cc7" |
| }, |
| { |
| "dataPath": "params_shard_27.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.11.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "943929ed6689421315b37de2069bac3e" |
| }, |
| { |
| "dataPath": "params_shard_28.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.11.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b7af20a632feeb691dad131c427361da" |
| }, |
| { |
| "dataPath": "params_shard_29.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.10.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.11.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.11.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.11.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "998e41ff0a772cc0ebfcbada5ba509be" |
| }, |
| { |
| "dataPath": "params_shard_30.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.12.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a55eb50e45079523e7118bb7d81ed0bc" |
| }, |
| { |
| "dataPath": "params_shard_31.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.12.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fe4425568398f561fdd86bcc3c590e29" |
| }, |
| { |
| "dataPath": "params_shard_32.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.12.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d3ca228bf4a18dae3c1c290ebbb9301b" |
| }, |
| { |
| "dataPath": "params_shard_33.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.12.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c75394a0865975a96cea82c4134b8013" |
| }, |
| { |
| "dataPath": "params_shard_34.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.11.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.12.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.12.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.12.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "3380b2725907bffa947a0f53a94f9be0" |
| }, |
| { |
| "dataPath": "params_shard_35.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.12.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6d993415a216929ad27350b2193fb884" |
| }, |
| { |
| "dataPath": "params_shard_36.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.13.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2dec49e4a00382867952370a2c846a58" |
| }, |
| { |
| "dataPath": "params_shard_37.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.13.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "64831b5f090ad3c3d502abca4646bd2c" |
| }, |
| { |
| "dataPath": "params_shard_38.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.13.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "23319bfacf264a48771dc7c8eaec4b5f" |
| }, |
| { |
| "dataPath": "params_shard_39.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.13.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d0309beb32bbf0984642d097f9837a5e" |
| }, |
| { |
| "dataPath": "params_shard_40.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.13.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a829e96d459ede0065e25f38e985b0e2" |
| }, |
| { |
| "dataPath": "params_shard_41.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.13.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "de271bba2ab37e4f1e6c289165285c12" |
| }, |
| { |
| "dataPath": "params_shard_42.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.12.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.12.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.13.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.13.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.13.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "e710ed6bb3b83ec0ecba8bac95e180c0" |
| }, |
| { |
| "dataPath": "params_shard_43.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.14.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f741a62d22afc5a471027dc3886941c0" |
| }, |
| { |
| "dataPath": "params_shard_44.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.14.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "77a77e4f9072a5a29045db1ee84b08d7" |
| }, |
| { |
| "dataPath": "params_shard_45.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.14.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f72cd576ba79aa0516babce9d89d943f" |
| }, |
| { |
| "dataPath": "params_shard_46.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.14.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6589e86407cde4a590967afdc9dced36" |
| }, |
| { |
| "dataPath": "params_shard_47.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.13.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.14.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.14.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.14.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "25e6c04eec076e0b53424555ebee0b5b" |
| }, |
| { |
| "dataPath": "params_shard_48.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.14.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5817f308b5fda6a97e6691f114124158" |
| }, |
| { |
| "dataPath": "params_shard_49.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.15.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d1dcdca44f2800cbe1de95a86fa7617c" |
| }, |
| { |
| "dataPath": "params_shard_50.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.15.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c247a751a81a72b75ce5da04b77be5d5" |
| }, |
| { |
| "dataPath": "params_shard_51.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.15.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "413f9d8405fb5e2615ec5c8c8a9e4ac5" |
| }, |
| { |
| "dataPath": "params_shard_52.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.15.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ce99b25d7f955a298fca7334c6e76137" |
| }, |
| { |
| "dataPath": "params_shard_53.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.15.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ad1f9ec6d428c2073cb43e22bcf6c55a" |
| }, |
| { |
| "dataPath": "params_shard_54.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.15.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5829f94338ce41a6bca0a90b9c0410b9" |
| }, |
| { |
| "dataPath": "params_shard_55.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.14.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.14.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.15.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.15.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.15.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "d67a39048d56045679e5a9e804da55e6" |
| }, |
| { |
| "dataPath": "params_shard_56.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.16.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fbfbc48b67a95b85a37ffb3dc604fc49" |
| }, |
| { |
| "dataPath": "params_shard_57.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.16.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "dfeb9c8cc2852a6d13c1fcb9a5e35e58" |
| }, |
| { |
| "dataPath": "params_shard_58.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.16.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8969413bc0c9f7594fdcac4a1375bb5e" |
| }, |
| { |
| "dataPath": "params_shard_59.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.16.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f92249c81db8b760e220eb65b44f2d87" |
| }, |
| { |
| "dataPath": "params_shard_60.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.15.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.16.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.16.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.16.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "5cce50a0f0576b3c6b6dbed86914770e" |
| }, |
| { |
| "dataPath": "params_shard_61.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.16.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cb54d2cd960c6fca75b3b13781977f88" |
| }, |
| { |
| "dataPath": "params_shard_62.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.17.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3c2107a1b1a2e5dc8e2f11f0417c99f6" |
| }, |
| { |
| "dataPath": "params_shard_63.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.17.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "311293b822dca4694f87119ab3159816" |
| }, |
| { |
| "dataPath": "params_shard_64.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.17.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1bde3138b9c35fe71e9445da71c7528a" |
| }, |
| { |
| "dataPath": "params_shard_65.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.17.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3743b57fd2fbaf1fce105b3a201f2fba" |
| }, |
| { |
| "dataPath": "params_shard_66.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.17.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8cdda00b96b521e82d2fec49c63d4ad8" |
| }, |
| { |
| "dataPath": "params_shard_67.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.17.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e4a47ada891664d73f2ee0dda19d7b8b" |
| }, |
| { |
| "dataPath": "params_shard_68.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.16.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.16.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.17.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.17.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.17.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "a1e0f9894461aeb146d953e1b61385c1" |
| }, |
| { |
| "dataPath": "params_shard_69.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.18.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b15d475d9b62fbe8571611cdfca1ec8c" |
| }, |
| { |
| "dataPath": "params_shard_70.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.18.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "60585805ec01ef87a88d6a4735bd57dd" |
| }, |
| { |
| "dataPath": "params_shard_71.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.18.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f18e6adbada4de32390c541e4d612ab7" |
| }, |
| { |
| "dataPath": "params_shard_72.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.18.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "914588e4e1aa8a7086fc2626438e4fae" |
| }, |
| { |
| "dataPath": "params_shard_73.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.17.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.18.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.18.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.18.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "983d68647ab5b0a62e4b8edde3047104" |
| }, |
| { |
| "dataPath": "params_shard_74.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.18.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4ebbfcfdf8f8b125b8750af91d17af3b" |
| }, |
| { |
| "dataPath": "params_shard_75.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.19.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "28df0049ed7adf44b22e5e063b3c2520" |
| }, |
| { |
| "dataPath": "params_shard_76.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.19.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2dd548d5e340ee9ecfddcb57ae713d3c" |
| }, |
| { |
| "dataPath": "params_shard_77.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.19.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d7eb301c110a7570cd7df92ec24ae8fb" |
| }, |
| { |
| "dataPath": "params_shard_78.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.19.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "73098eb1f4aa354bbd8581d6a3e19fec" |
| }, |
| { |
| "dataPath": "params_shard_79.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.19.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a896c76b29da2bfe4179f75929194556" |
| }, |
| { |
| "dataPath": "params_shard_80.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.19.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d3a976b607b7db8c13589c407c6f23f6" |
| }, |
| { |
| "dataPath": "params_shard_81.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.18.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.18.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.19.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.19.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.19.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "f7b4c2ba2268d37505c0277ca0358b12" |
| }, |
| { |
| "dataPath": "params_shard_82.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.2.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "646097f50d22b63383af3e083c0b1ab5" |
| }, |
| { |
| "dataPath": "params_shard_83.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.2.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cbcd318e80b4d79179273fee2d6b2ab5" |
| }, |
| { |
| "dataPath": "params_shard_84.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.2.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0a615ccdb2efcb6c9f66b78fadf422e9" |
| }, |
| { |
| "dataPath": "params_shard_85.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.2.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e671ba32e9945fc2c244da89891fae28" |
| }, |
| { |
| "dataPath": "params_shard_86.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.19.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.2.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.2.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.2.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "e9acba37827c99fbd080983e5473f903" |
| }, |
| { |
| "dataPath": "params_shard_87.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b7c050e9502149204166cb4f6be0fa09" |
| }, |
| { |
| "dataPath": "params_shard_88.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.20.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "990c6d22f804a8fe478dfe55a4a02538" |
| }, |
| { |
| "dataPath": "params_shard_89.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.20.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f0dc4118af43806f9aeaa29a60f2f3dd" |
| }, |
| { |
| "dataPath": "params_shard_90.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.20.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2393b2f17fb5be2d12e12a3a8686cfa0" |
| }, |
| { |
| "dataPath": "params_shard_91.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.20.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "82b16cc7e5b201da648c0e2f74b001cc" |
| }, |
| { |
| "dataPath": "params_shard_92.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.20.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e130b80fb81e4187522b60101f7cd4b4" |
| }, |
| { |
| "dataPath": "params_shard_93.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1c9b31bb3c4c12ef81b762b8361a8315" |
| }, |
| { |
| "dataPath": "params_shard_94.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.2.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.20.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.20.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.20.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "ab592bf3b2f2cbab30a42e12ef888c6f" |
| }, |
| { |
| "dataPath": "params_shard_95.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.21.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5bdf0f08976db35d74a4cce9a4a16e3b" |
| }, |
| { |
| "dataPath": "params_shard_96.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.21.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e3cb44717e858983494d6c5c9f6715b7" |
| }, |
| { |
| "dataPath": "params_shard_97.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.21.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fb65c0b988bce9eae675d2206bc9bff9" |
| }, |
| { |
| "dataPath": "params_shard_98.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.21.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "76f279ea704dd10c598c3a57a7a366a4" |
| }, |
| { |
| "dataPath": "params_shard_99.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.21.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.21.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.21.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "45a755234c1ca97bec5bbe0ac7f2f56a" |
| }, |
| { |
| "dataPath": "params_shard_100.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.21.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4eb3dd2894ca58029a345aae397cce3b" |
| }, |
| { |
| "dataPath": "params_shard_101.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.22.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9fc444d9677e9d77058f4179a05ad42c" |
| }, |
| { |
| "dataPath": "params_shard_102.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.22.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3e40d4fe6f4a051c7b957f81195d8004" |
| }, |
| { |
| "dataPath": "params_shard_103.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.22.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d15bb9ce56d735f5fc07d849d0881a93" |
| }, |
| { |
| "dataPath": "params_shard_104.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.22.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2f95f2ee1c5aed403406e78e03bf6cde" |
| }, |
| { |
| "dataPath": "params_shard_105.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.22.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "09dfc4df36c0ac9278aeb6273a652759" |
| }, |
| { |
| "dataPath": "params_shard_106.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f2f8b95d2003c7114abb31f9fee75f41" |
| }, |
| { |
| "dataPath": "params_shard_107.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.21.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.21.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.22.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.22.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.22.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "2b972e2119eb5334c22f6db30923d067" |
| }, |
| { |
| "dataPath": "params_shard_108.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.23.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cdffd91b606ac800ba7029972997435d" |
| }, |
| { |
| "dataPath": "params_shard_109.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.23.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7fc3e4fb99e4a708b35020e25fd02c43" |
| }, |
| { |
| "dataPath": "params_shard_110.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.23.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "733d6a1c3022967b5cd886b3703cf25f" |
| }, |
| { |
| "dataPath": "params_shard_111.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.23.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7af827b7979ac54179f90faedc4d1318" |
| }, |
| { |
| "dataPath": "params_shard_112.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.23.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.23.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.23.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "5608aea9f9c50189097991b3ba3865c9" |
| }, |
| { |
| "dataPath": "params_shard_113.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.23.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4cf5496e79a5f4ec8e5def35f6bb9910" |
| }, |
| { |
| "dataPath": "params_shard_114.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.24.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9c431d168989ff4b7a09e9fbb1f02019" |
| }, |
| { |
| "dataPath": "params_shard_115.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.24.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "da62b2b660c1af74fb6dbd77bcd6ddc3" |
| }, |
| { |
| "dataPath": "params_shard_116.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.24.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "883cab5496c0f1558b8a26921bd37961" |
| }, |
| { |
| "dataPath": "params_shard_117.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.24.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6d06dfa3bff6826fa5f74d7d421e6ef1" |
| }, |
| { |
| "dataPath": "params_shard_118.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.24.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e55c1d28332126536f1c2ba423b263ee" |
| }, |
| { |
| "dataPath": "params_shard_119.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.24.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ff55402de48b09d92d7841d4cf369050" |
| }, |
| { |
| "dataPath": "params_shard_120.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.23.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.23.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.24.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.24.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.24.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "92d7d4730c19273e61134e9783a9a86c" |
| }, |
| { |
| "dataPath": "params_shard_121.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.25.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6d60b708e122b5458e897a3ef8987e7a" |
| }, |
| { |
| "dataPath": "params_shard_122.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.25.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e139f7fd0895c9fbeb2daf00fbfb1b0a" |
| }, |
| { |
| "dataPath": "params_shard_123.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.25.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "89e7c5c1918da977f7840fe58239b211" |
| }, |
| { |
| "dataPath": "params_shard_124.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.25.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "030409d0b38e585fe23c5dc5f18d165e" |
| }, |
| { |
| "dataPath": "params_shard_125.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.24.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.25.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.25.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.25.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "7805b6e35f4c041567178c8444ddb744" |
| }, |
| { |
| "dataPath": "params_shard_126.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.25.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "35828a12ae5634eb74701143ae10d8bd" |
| }, |
| { |
| "dataPath": "params_shard_127.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.26.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0e68e89c6b520a138c8f22d161eaa279" |
| }, |
| { |
| "dataPath": "params_shard_128.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.26.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c785d9c502f1c1430adc4aeba21c9409" |
| }, |
| { |
| "dataPath": "params_shard_129.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.26.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ef1cf9c72f3208996413ecc991c2a06f" |
| }, |
| { |
| "dataPath": "params_shard_130.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.26.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "05590537c954cce0a6113314dbe0b95a" |
| }, |
| { |
| "dataPath": "params_shard_131.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.26.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e53b9f9a456eeb6c942bbe6f799a5aba" |
| }, |
| { |
| "dataPath": "params_shard_132.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.26.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "037df20b1cc0b66511fc9c1b60a9f511" |
| }, |
| { |
| "dataPath": "params_shard_133.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.25.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.25.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.26.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.26.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.26.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "bfecfc782c01ed5050da306e90832d8f" |
| }, |
| { |
| "dataPath": "params_shard_134.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.27.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0367048208636b31b7efb560ec8ab083" |
| }, |
| { |
| "dataPath": "params_shard_135.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.27.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fb1c6a096fb53cff8027ccbec4036a5f" |
| }, |
| { |
| "dataPath": "params_shard_136.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.27.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b59d2ab77f2e71cefb0ebc50a68c047c" |
| }, |
| { |
| "dataPath": "params_shard_137.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.27.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2e4fd79f777ecdcffd8f1dc06001c15e" |
| }, |
| { |
| "dataPath": "params_shard_138.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.26.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.27.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.27.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.27.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "d445cc2304c72c46a0e456ec8a6ff4fe" |
| }, |
| { |
| "dataPath": "params_shard_139.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.27.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "942588e1a0b7da4cb5eeaf4a9e187632" |
| }, |
| { |
| "dataPath": "params_shard_140.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.28.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0310c29489167467e52633475e8bc21b" |
| }, |
| { |
| "dataPath": "params_shard_141.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.28.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c0d8d54fd7d729586f02b4b1f7c9cef0" |
| }, |
| { |
| "dataPath": "params_shard_142.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.28.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0f8570fe20c43233c51e00716d481a55" |
| }, |
| { |
| "dataPath": "params_shard_143.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.28.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "767be0f845f9604c6c19f9ec6a72177f" |
| }, |
| { |
| "dataPath": "params_shard_144.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.28.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d02409f877d540b5f7630a540927fe24" |
| }, |
| { |
| "dataPath": "params_shard_145.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.28.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6e4a3c46028ceccaf7044899c00305fa" |
| }, |
| { |
| "dataPath": "params_shard_146.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.27.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.27.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.28.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.28.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.28.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "4dbdd9688978c0a169284be2e2323732" |
| }, |
| { |
| "dataPath": "params_shard_147.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.29.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "62454910cb3f586c044fd637a2acd7bd" |
| }, |
| { |
| "dataPath": "params_shard_148.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.29.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9f49f5eebb6fcef8d5a9bda7c305dc2a" |
| }, |
| { |
| "dataPath": "params_shard_149.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.29.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d14b3e01c25f628568428a69c1dddff6" |
| }, |
| { |
| "dataPath": "params_shard_150.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.29.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "681663fe79f92bb4a528fa0fa0a7ccf2" |
| }, |
| { |
| "dataPath": "params_shard_151.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.28.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.29.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.29.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.29.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "e227c1c47411ed43f3ff12b1310bc76a" |
| }, |
| { |
| "dataPath": "params_shard_152.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.29.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a9f6b059e4daf1d3e2efd4be78fd90e4" |
| }, |
| { |
| "dataPath": "params_shard_153.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.3.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1bb31a972f4f4b0909ca18d79d8264cd" |
| }, |
| { |
| "dataPath": "params_shard_154.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.3.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fff6228a62b0fba431f5f30058997a18" |
| }, |
| { |
| "dataPath": "params_shard_155.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.3.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c766773126c51915565db77c8c2aaa0e" |
| }, |
| { |
| "dataPath": "params_shard_156.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.3.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b4d476c22ec4433969d7300d618373a2" |
| }, |
| { |
| "dataPath": "params_shard_157.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.3.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0c82b8639b750861b365e14a28b593df" |
| }, |
| { |
| "dataPath": "params_shard_158.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1c7e2796d96a86d25ece8d40eb7e31d0" |
| }, |
| { |
| "dataPath": "params_shard_159.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.29.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.29.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.3.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.3.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.3.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "23485e116c321bf588470d296ee79aa8" |
| }, |
| { |
| "dataPath": "params_shard_160.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.30.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8fc6f5bd1b47273571f196a065300067" |
| }, |
| { |
| "dataPath": "params_shard_161.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.30.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7fbed5c1668358a3f812d6e929e5b299" |
| }, |
| { |
| "dataPath": "params_shard_162.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.30.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6e4c7a11d972aa7b1339bef003adc222" |
| }, |
| { |
| "dataPath": "params_shard_163.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.30.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "50f3c37b69e0248c6c59677536b5602b" |
| }, |
| { |
| "dataPath": "params_shard_164.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.30.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.30.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.30.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "e673eacec01473b764678a6f4f83b93c" |
| }, |
| { |
| "dataPath": "params_shard_165.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.30.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e8d5627a6d55f9f3a352ae34c03083b6" |
| }, |
| { |
| "dataPath": "params_shard_166.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.31.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3110ac8d7b136384ac68e826b2155d8a" |
| }, |
| { |
| "dataPath": "params_shard_167.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.31.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "dbe2a6715f84892f3ef39efaaa3cc0be" |
| }, |
| { |
| "dataPath": "params_shard_168.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.31.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3ab9575dad5d0472e398f71227cdac97" |
| }, |
| { |
| "dataPath": "params_shard_169.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.31.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e826e8521a498714d29588377657d2d6" |
| }, |
| { |
| "dataPath": "params_shard_170.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.31.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6ecba117cd462c5c1eb9c4bdee2b8c25" |
| }, |
| { |
| "dataPath": "params_shard_171.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.31.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2252098ee278d4199e3129c9bb058e58" |
| }, |
| { |
| "dataPath": "params_shard_172.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.30.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.30.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.31.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.31.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.31.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "7c90e6988e0acca94e87f92a5b7fb226" |
| }, |
| { |
| "dataPath": "params_shard_173.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.32.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "86109611dc68dfb184b254336172e926" |
| }, |
| { |
| "dataPath": "params_shard_174.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.32.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2486e7d881c9d1b8164e50d31a46489a" |
| }, |
| { |
| "dataPath": "params_shard_175.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.32.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6ae3950a7909ac19359e2fa1114535cd" |
| }, |
| { |
| "dataPath": "params_shard_176.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.32.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "10a0457d2adf3a1ad8ac5b7330e9a6ee" |
| }, |
| { |
| "dataPath": "params_shard_177.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.31.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.32.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.32.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.32.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "c232f6cc6f51f817a129eb346717d184" |
| }, |
| { |
| "dataPath": "params_shard_178.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.32.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "85ed85a077c803e2517d2ff0e720a285" |
| }, |
| { |
| "dataPath": "params_shard_179.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.33.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "60677e0c4294e01360fec3d13823a013" |
| }, |
| { |
| "dataPath": "params_shard_180.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.33.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fab0f371fd0683c0bfc4b88f77d92d68" |
| }, |
| { |
| "dataPath": "params_shard_181.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.33.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "85cfe3a392fd4bc937b190eaca4afb6d" |
| }, |
| { |
| "dataPath": "params_shard_182.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.33.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c969eb7d34ff5c11807fe85ead81f37c" |
| }, |
| { |
| "dataPath": "params_shard_183.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.33.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "aa671f42fe626ee3342d46fcd7b3628a" |
| }, |
| { |
| "dataPath": "params_shard_184.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.33.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e9cc25e0893ed512b9b2967da9826d2b" |
| }, |
| { |
| "dataPath": "params_shard_185.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.32.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.32.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.33.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.33.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.33.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "d3ec5c226762c0d95caef324c15e8c5a" |
| }, |
| { |
| "dataPath": "params_shard_186.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.34.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "861746a5d0844c31fe72ecf5a1c07ecb" |
| }, |
| { |
| "dataPath": "params_shard_187.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.34.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "acc22497da2cb73ccaf74d7151a093d6" |
| }, |
| { |
| "dataPath": "params_shard_188.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.34.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4354b3739a07ccdecab74fd68b415662" |
| }, |
| { |
| "dataPath": "params_shard_189.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.34.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cfeda0eec787e6117e9861d00b103a42" |
| }, |
| { |
| "dataPath": "params_shard_190.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.33.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.34.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.34.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.34.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "2d4cc37369977eb38d6c3197c57fd35f" |
| }, |
| { |
| "dataPath": "params_shard_191.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.34.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "57f949ef4475bc5b1ce545dcb99a6ae7" |
| }, |
| { |
| "dataPath": "params_shard_192.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.35.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "491d5468aa88d61cd2a226357124c161" |
| }, |
| { |
| "dataPath": "params_shard_193.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.35.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "31ae07f7efc554faa3dd7692c0ce4b0b" |
| }, |
| { |
| "dataPath": "params_shard_194.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.35.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "bdffd9de94e3c2b7c5abe3b9114bead9" |
| }, |
| { |
| "dataPath": "params_shard_195.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.35.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2e3cd65a5f365b9654fee016eebd9385" |
| }, |
| { |
| "dataPath": "params_shard_196.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.35.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "35bcb3f9b68a59c8327200351bfb7c27" |
| }, |
| { |
| "dataPath": "params_shard_197.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.35.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "aedf40169b5f970842c18e3a7add3b3b" |
| }, |
| { |
| "dataPath": "params_shard_198.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.34.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.34.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.35.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.35.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.35.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "ffb43624392b558217541c08f929173b" |
| }, |
| { |
| "dataPath": "params_shard_199.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.36.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d52dbcf67949fe694dadb93dc890ae09" |
| }, |
| { |
| "dataPath": "params_shard_200.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.36.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "264e8f8ded2fd56301724e20154ae548" |
| }, |
| { |
| "dataPath": "params_shard_201.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.36.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6a2ebf312f1aa9e83696c332d1832186" |
| }, |
| { |
| "dataPath": "params_shard_202.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.36.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d21ba8df53d765ac378ea38f14511aca" |
| }, |
| { |
| "dataPath": "params_shard_203.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.35.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.36.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.36.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.36.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "77967831d65e3d4990e4d72d247d0880" |
| }, |
| { |
| "dataPath": "params_shard_204.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.36.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "71bcb3c5fa64413eac44c27733a0bb4b" |
| }, |
| { |
| "dataPath": "params_shard_205.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.37.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "074cc352573e4fbdf5abf5c38fd191d4" |
| }, |
| { |
| "dataPath": "params_shard_206.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.37.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7250898db9511f85965af06b1815720e" |
| }, |
| { |
| "dataPath": "params_shard_207.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.37.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4b97bef43e2b44d6cbcdd8e3231f64cc" |
| }, |
| { |
| "dataPath": "params_shard_208.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.37.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "903e2ab6eda2223fa61ee2b29bfd3579" |
| }, |
| { |
| "dataPath": "params_shard_209.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.37.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e8cdf28e8d9a9474848401c54992c6c6" |
| }, |
| { |
| "dataPath": "params_shard_210.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.37.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2e12ddf092fe20ab9755889dbe1906f6" |
| }, |
| { |
| "dataPath": "params_shard_211.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.36.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.36.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.37.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.37.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.37.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "18df2199c0413f18bdada023c27f3729" |
| }, |
| { |
| "dataPath": "params_shard_212.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.38.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "abfd106f104d87c5d7f94e1dafe1cc65" |
| }, |
| { |
| "dataPath": "params_shard_213.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.38.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4f73c38984d270d0d537a7a0d76aeaa8" |
| }, |
| { |
| "dataPath": "params_shard_214.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.38.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8a098c78e059547c7b6aefc9fe454409" |
| }, |
| { |
| "dataPath": "params_shard_215.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.38.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e56b1b18cd11c7d1ff36974ecc934be3" |
| }, |
| { |
| "dataPath": "params_shard_216.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.37.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.38.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.38.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.38.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "4f299eab68b280e1a6a4dafe5bf49360" |
| }, |
| { |
| "dataPath": "params_shard_217.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.38.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2f34cbf3e88af7157a53da6f616f573f" |
| }, |
| { |
| "dataPath": "params_shard_218.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.39.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "715b7c77f40e0c88eb792de87b0cd372" |
| }, |
| { |
| "dataPath": "params_shard_219.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.39.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "55da788d270616cea5d04916bb48a8b7" |
| }, |
| { |
| "dataPath": "params_shard_220.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.39.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b3c53df81ecccfa918a44703789580cb" |
| }, |
| { |
| "dataPath": "params_shard_221.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.39.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9fb35e059e3243e0db00a691a786a895" |
| }, |
| { |
| "dataPath": "params_shard_222.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.39.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ab58b47d890b7eea05b2b44f65090291" |
| }, |
| { |
| "dataPath": "params_shard_223.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.39.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ac0e1e4d52fa22c19544a087e93f9eb7" |
| }, |
| { |
| "dataPath": "params_shard_224.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.38.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.38.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.39.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.39.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.39.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "731e11156c27de3534950f1405b0d171" |
| }, |
| { |
| "dataPath": "params_shard_225.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.4.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e104c15932df6d8868d666ee0cf842d3" |
| }, |
| { |
| "dataPath": "params_shard_226.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.4.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b15657bcacd603f6ec7f4166992f78b2" |
| }, |
| { |
| "dataPath": "params_shard_227.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.4.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3ebaafde67385c6d6db3f326a211fe11" |
| }, |
| { |
| "dataPath": "params_shard_228.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.4.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "82860eb9c3ed8c19956bead529a746b7" |
| }, |
| { |
| "dataPath": "params_shard_229.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.39.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.4.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.4.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.4.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "8909e081c9f7889cf7a917405ca4f03a" |
| }, |
| { |
| "dataPath": "params_shard_230.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "389be6e5a89998cedeab8b6a93f73214" |
| }, |
| { |
| "dataPath": "params_shard_231.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.40.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "69e2f544372148a5b35e61adfe838e85" |
| }, |
| { |
| "dataPath": "params_shard_232.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.40.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0414f64b81215af31dfcc3da5172b1b6" |
| }, |
| { |
| "dataPath": "params_shard_233.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.40.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b2e99acae1e17de5ccd9274d5d1136eb" |
| }, |
| { |
| "dataPath": "params_shard_234.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.40.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cd7564fabc7c1e6a9aa92352750ae8d7" |
| }, |
| { |
| "dataPath": "params_shard_235.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.40.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9c0c5fbe74a86d133f8a808c5eea2896" |
| }, |
| { |
| "dataPath": "params_shard_236.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.40.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8a475ab5012fac2ded5886a5b6462641" |
| }, |
| { |
| "dataPath": "params_shard_237.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.4.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.40.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.40.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.40.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "576fba612f1804be20a32c3e08ee6e1d" |
| }, |
| { |
| "dataPath": "params_shard_238.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.41.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1c62f3b453fea44b0d9934bda08ad699" |
| }, |
| { |
| "dataPath": "params_shard_239.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.41.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "26ae0b055f8600cc9a16916a12ebbf7b" |
| }, |
| { |
| "dataPath": "params_shard_240.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.41.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8e68aa9c1eef3ae34e7a30a700bd2086" |
| }, |
| { |
| "dataPath": "params_shard_241.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.41.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3d866f11a709fb56dd2b413299ca851f" |
| }, |
| { |
| "dataPath": "params_shard_242.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.40.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.41.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.41.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.41.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "d381f9e31339fa6446e8773b4bc27f8b" |
| }, |
| { |
| "dataPath": "params_shard_243.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.41.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ec7d5bb944940347d825561e681842c9" |
| }, |
| { |
| "dataPath": "params_shard_244.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.42.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c43808381247439354a22f3cfe2c51aa" |
| }, |
| { |
| "dataPath": "params_shard_245.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.42.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3b6db14047f7d0a36bf8c7fc57a2cda4" |
| }, |
| { |
| "dataPath": "params_shard_246.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.42.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "25ea43caa512e5ce09ff52afbd0a655e" |
| }, |
| { |
| "dataPath": "params_shard_247.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.42.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "08815fd940bf3db2578f11fa42822b8b" |
| }, |
| { |
| "dataPath": "params_shard_248.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.42.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a4bc823c5ea6dbcab36f4968c8c5beb0" |
| }, |
| { |
| "dataPath": "params_shard_249.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.42.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "30f5296efd1f60a35664d102768d7f6b" |
| }, |
| { |
| "dataPath": "params_shard_250.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.41.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.41.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.42.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.42.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.42.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "508a2a39b119af8059ce6a2e171706a8" |
| }, |
| { |
| "dataPath": "params_shard_251.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.43.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "86e20d245d13c87d93a2b5dc9ff1581e" |
| }, |
| { |
| "dataPath": "params_shard_252.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.43.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e5e451a685c12930645cb11ebebd14b8" |
| }, |
| { |
| "dataPath": "params_shard_253.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.43.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1101764b3a971f4988d95cadbff4bd10" |
| }, |
| { |
| "dataPath": "params_shard_254.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.43.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "13f3b12ace1f08d104a1663998898521" |
| }, |
| { |
| "dataPath": "params_shard_255.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.42.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.43.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.43.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.43.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "f02193072009880e34dfb643601c1b12" |
| }, |
| { |
| "dataPath": "params_shard_256.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.43.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "dcb11d71caa848b904a101b038b8e2e7" |
| }, |
| { |
| "dataPath": "params_shard_257.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.44.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3adb8d01e1de0289aa3947dc12edb980" |
| }, |
| { |
| "dataPath": "params_shard_258.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.44.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c6e35a48030fe669f0762760771715f4" |
| }, |
| { |
| "dataPath": "params_shard_259.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.44.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "95381ec19b14b1abe240c97fd1769fa2" |
| }, |
| { |
| "dataPath": "params_shard_260.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.44.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "59f00a27c0aefdf58785c97c56f7a119" |
| }, |
| { |
| "dataPath": "params_shard_261.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.44.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0c93933fde6b0c64517f4c20215c17ec" |
| }, |
| { |
| "dataPath": "params_shard_262.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.44.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7bfe854679e47234cec34ce2cc045356" |
| }, |
| { |
| "dataPath": "params_shard_263.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.43.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.43.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.44.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.44.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.44.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "04f9c2e05a5846156a6ac9a2b63a8988" |
| }, |
| { |
| "dataPath": "params_shard_264.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.45.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "28dae7801cec36fdc417288b5fd5d3e8" |
| }, |
| { |
| "dataPath": "params_shard_265.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.45.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c4613237e8d75c825acfbdf70eb46326" |
| }, |
| { |
| "dataPath": "params_shard_266.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.45.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "692d26695a3ed6042a119e14dc0cd240" |
| }, |
| { |
| "dataPath": "params_shard_267.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.45.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6dcf8591455eb2d1245dc544d2e2325a" |
| }, |
| { |
| "dataPath": "params_shard_268.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.44.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.45.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.45.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.45.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "e739522a7b30e47ba8cd96781a49afec" |
| }, |
| { |
| "dataPath": "params_shard_269.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.45.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1e19b073c7f012617054edb40e49cb6b" |
| }, |
| { |
| "dataPath": "params_shard_270.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.46.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "17170f8edcaf66b8e0928535aa07a09b" |
| }, |
| { |
| "dataPath": "params_shard_271.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.46.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "562670ff05c0fc76bdc1ae3acf7b4b01" |
| }, |
| { |
| "dataPath": "params_shard_272.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.46.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "345e0559d93320007512ac72ee153d99" |
| }, |
| { |
| "dataPath": "params_shard_273.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.46.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9d27c4f8bb41ffeb00a1a965b6ccf7b7" |
| }, |
| { |
| "dataPath": "params_shard_274.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.46.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c321bc1f57d6a48d65a8b15bd64b0f6d" |
| }, |
| { |
| "dataPath": "params_shard_275.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.46.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e9d9ef277bc94d7d18ca4baf55258020" |
| }, |
| { |
| "dataPath": "params_shard_276.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.45.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.45.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.46.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.46.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.46.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "e5fb4c9814f02f773821ba2f4a15a170" |
| }, |
| { |
| "dataPath": "params_shard_277.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.47.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "29f087c8767002971666433d6a86bdc6" |
| }, |
| { |
| "dataPath": "params_shard_278.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.47.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "869f1912e1fa4c903d8e6511a015db4e" |
| }, |
| { |
| "dataPath": "params_shard_279.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.47.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e8b3913aee73b883b535881dda4e31a0" |
| }, |
| { |
| "dataPath": "params_shard_280.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.47.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0c573fc3037ad3c01ed24dd9ce474441" |
| }, |
| { |
| "dataPath": "params_shard_281.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.46.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.47.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.47.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.47.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "b375aae94fd29b0372cf9bfdc561d3d0" |
| }, |
| { |
| "dataPath": "params_shard_282.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.47.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3eb43436d9af75ee3ce6cc1430f86107" |
| }, |
| { |
| "dataPath": "params_shard_283.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.48.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9a81fdd35d4d117087a0c869d2240723" |
| }, |
| { |
| "dataPath": "params_shard_284.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.48.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1c7b3d400418550acda4eb3cdbfccb3f" |
| }, |
| { |
| "dataPath": "params_shard_285.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.48.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "008ee18694f737470d95768dbc2ab8c4" |
| }, |
| { |
| "dataPath": "params_shard_286.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.48.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "684d5a548a0b374a11f1847ff7ec29e4" |
| }, |
| { |
| "dataPath": "params_shard_287.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.48.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f53ceae6aafcc91d32270b03e2c02f35" |
| }, |
| { |
| "dataPath": "params_shard_288.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.48.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "603ac3a00138b2f8a02c107caa796038" |
| }, |
| { |
| "dataPath": "params_shard_289.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.47.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.47.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.48.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.48.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.48.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "e9178d3ba3dbb77a6e3b8cf7499ae8a9" |
| }, |
| { |
| "dataPath": "params_shard_290.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.49.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "36afc3e61ff1faa5c663029390856a28" |
| }, |
| { |
| "dataPath": "params_shard_291.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.49.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9ed440ff7e85e2cb9f0e587bd43a5e25" |
| }, |
| { |
| "dataPath": "params_shard_292.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.49.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "123544b294dde19c68c445c3d15a2c15" |
| }, |
| { |
| "dataPath": "params_shard_293.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.49.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f4c20ce87f99d8919a34b9a5406b3e1a" |
| }, |
| { |
| "dataPath": "params_shard_294.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.48.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.49.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.49.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.49.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "bf7ead1827b2b41b5bb160184d9cb558" |
| }, |
| { |
| "dataPath": "params_shard_295.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.49.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "11dbff7e5aecead225b424969859b88a" |
| }, |
| { |
| "dataPath": "params_shard_296.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.5.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ab90c505bd826b3c03ebd8c7c07af9d5" |
| }, |
| { |
| "dataPath": "params_shard_297.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.5.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ab1a43e75fa2f6d2548b6c6956fcb7b6" |
| }, |
| { |
| "dataPath": "params_shard_298.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.5.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ab312c27c46e1067a0968ae8406f0190" |
| }, |
| { |
| "dataPath": "params_shard_299.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.5.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cf96e03f749552073eec1a4224a518cb" |
| }, |
| { |
| "dataPath": "params_shard_300.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.5.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e58f2461399c2f14a4e3a7be70cf66ec" |
| }, |
| { |
| "dataPath": "params_shard_301.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3389970550bfd9b826279dd2627fe41b" |
| }, |
| { |
| "dataPath": "params_shard_302.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.49.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.49.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.5.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.5.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.5.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "3e4330cda9013de24f931d0b8f83e41e" |
| }, |
| { |
| "dataPath": "params_shard_303.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.50.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "413c7991d796dbc12c0e382c2e217b2e" |
| }, |
| { |
| "dataPath": "params_shard_304.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.50.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "564b9fe353a14d10a0acba15f7ad8ab9" |
| }, |
| { |
| "dataPath": "params_shard_305.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.50.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "dfba45ce6bd1593d393f294b7494d00a" |
| }, |
| { |
| "dataPath": "params_shard_306.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.50.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9c776bc3d2420ef14236d4f3c1e9329a" |
| }, |
| { |
| "dataPath": "params_shard_307.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.50.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.50.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.50.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "4a9cae047cf0c8580bf894be86dff4db" |
| }, |
| { |
| "dataPath": "params_shard_308.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.50.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a227328db278af6ffce2ce82f93bd1ef" |
| }, |
| { |
| "dataPath": "params_shard_309.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.51.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1f869143737cf6acd0a02e5760764bf1" |
| }, |
| { |
| "dataPath": "params_shard_310.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.51.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ee7573ba9d9677b7fc60b4a7dad63cb2" |
| }, |
| { |
| "dataPath": "params_shard_311.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.51.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "435fb657075e8a53a28766088ee392b3" |
| }, |
| { |
| "dataPath": "params_shard_312.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.51.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ca31251516a9e2aaf047bcbf48f333cd" |
| }, |
| { |
| "dataPath": "params_shard_313.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.51.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0ce6dbdff7489aabf43f0d4739a37e0a" |
| }, |
| { |
| "dataPath": "params_shard_314.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.51.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "db0bb032398c754b8e3557bd892a2ee2" |
| }, |
| { |
| "dataPath": "params_shard_315.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.50.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.50.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.51.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.51.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.51.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "d2848df80a86cdd4321bcd2d23895a4a" |
| }, |
| { |
| "dataPath": "params_shard_316.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.52.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "918bf1ef5f639668a933bf6092aa980b" |
| }, |
| { |
| "dataPath": "params_shard_317.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.52.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8e4d9efa6b1f4a1763cb86c11154bad7" |
| }, |
| { |
| "dataPath": "params_shard_318.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.52.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b1fc6046c5e75ea27dd3a34a656c9240" |
| }, |
| { |
| "dataPath": "params_shard_319.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.52.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cbe7dfec6e7c4dc7405525538fd5a197" |
| }, |
| { |
| "dataPath": "params_shard_320.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.51.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.52.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.52.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.52.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "075e85305fd2a7fc08aab4f0bbb4ae9e" |
| }, |
| { |
| "dataPath": "params_shard_321.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.52.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9e255fc7723fd9d3b147331cac5633fa" |
| }, |
| { |
| "dataPath": "params_shard_322.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.53.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "81780e8485862d723ba338788b508613" |
| }, |
| { |
| "dataPath": "params_shard_323.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.53.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3b8a07d30911f70c436602b7d354531b" |
| }, |
| { |
| "dataPath": "params_shard_324.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.53.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "da5b7b1100363ac8053a8b04cd37e3f9" |
| }, |
| { |
| "dataPath": "params_shard_325.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.53.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "12163f0d8d60d3a29d7b311769574667" |
| }, |
| { |
| "dataPath": "params_shard_326.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.53.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "624ea996db2d8c0f9c95a829fb07f095" |
| }, |
| { |
| "dataPath": "params_shard_327.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.53.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f0074369d31ac5bc9ea32f9f9219e6df" |
| }, |
| { |
| "dataPath": "params_shard_328.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.52.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.52.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.53.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.53.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.53.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "02597d5887e6748de0f775233d162c23" |
| }, |
| { |
| "dataPath": "params_shard_329.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.54.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "99c2ff762d8dc474f82ef7df2640e079" |
| }, |
| { |
| "dataPath": "params_shard_330.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.54.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cda48e075f8f13bca4c3e0b65aea7610" |
| }, |
| { |
| "dataPath": "params_shard_331.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.54.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "df870da7ac24b153725bce5c30937d12" |
| }, |
| { |
| "dataPath": "params_shard_332.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.54.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4a3b102c8a434c4cd38477a1bcd653a0" |
| }, |
| { |
| "dataPath": "params_shard_333.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.53.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.54.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.54.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.54.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "1399c919c8884638157689047e7a5930" |
| }, |
| { |
| "dataPath": "params_shard_334.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.54.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d1d7e47b9260c2af669462cf66712973" |
| }, |
| { |
| "dataPath": "params_shard_335.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.55.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "acffcf1699b1c502893671fc81e2098d" |
| }, |
| { |
| "dataPath": "params_shard_336.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.55.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d312868852e4e4dba6e4086139c4f527" |
| }, |
| { |
| "dataPath": "params_shard_337.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.55.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c44360f4beafea7dd7ff5e722fa0dd02" |
| }, |
| { |
| "dataPath": "params_shard_338.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.55.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f036d11adcce70a21b86f9955e2ee34f" |
| }, |
| { |
| "dataPath": "params_shard_339.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.55.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ddf61a5c3f5a79941b06f5e92f6a2a09" |
| }, |
| { |
| "dataPath": "params_shard_340.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.55.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5d3d37e4499b5afcb5a22fa420386c5f" |
| }, |
| { |
| "dataPath": "params_shard_341.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.54.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.54.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.55.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.55.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.55.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "b8d757917fa7bd439387bff0814b3bc0" |
| }, |
| { |
| "dataPath": "params_shard_342.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.56.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4b3fcf9a8131904322f4eab4874f001f" |
| }, |
| { |
| "dataPath": "params_shard_343.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.56.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f38e0f5c71723b5bc77765448d12724e" |
| }, |
| { |
| "dataPath": "params_shard_344.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.56.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9d83843d7d04e54b0780f9c2cbd1672c" |
| }, |
| { |
| "dataPath": "params_shard_345.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.56.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e566c80de18001ad45fa317d06e9b189" |
| }, |
| { |
| "dataPath": "params_shard_346.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.55.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.56.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.56.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.56.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "d9363756ce4dbe5f1831f26103b3592b" |
| }, |
| { |
| "dataPath": "params_shard_347.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.56.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "20d23306ed67bb96426e2ca3f988a87c" |
| }, |
| { |
| "dataPath": "params_shard_348.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.57.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0f72f18866f5dd2b3062d0b1b437e541" |
| }, |
| { |
| "dataPath": "params_shard_349.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.57.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ea6f2d3569e523a7e465f689fe660dce" |
| }, |
| { |
| "dataPath": "params_shard_350.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.57.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b3dc7a80b4376aad295cce1bbcce89a9" |
| }, |
| { |
| "dataPath": "params_shard_351.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.57.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "482dce7adaf256be8d2c2db8361481ee" |
| }, |
| { |
| "dataPath": "params_shard_352.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.57.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "386b318227407daea7355f1c090e92a7" |
| }, |
| { |
| "dataPath": "params_shard_353.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.57.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ccb565f0219e73facc4b221091ea26e5" |
| }, |
| { |
| "dataPath": "params_shard_354.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.56.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.56.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.57.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.57.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.57.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "6ecdb98b4296c90a8d5d215e362562b8" |
| }, |
| { |
| "dataPath": "params_shard_355.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.58.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "79bd48f43f976c9e6054054fe5eebf6c" |
| }, |
| { |
| "dataPath": "params_shard_356.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.58.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fcbb5dff2849a1c28ec8844d982e45d3" |
| }, |
| { |
| "dataPath": "params_shard_357.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.58.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "22ab7f895c93fd9ee62e09db7efdd24e" |
| }, |
| { |
| "dataPath": "params_shard_358.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.58.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0fd2125786fcf02ff92ac02ddb3ceeed" |
| }, |
| { |
| "dataPath": "params_shard_359.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.57.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.58.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.58.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.58.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "b5653e35214500f0ecb8c7caa10669ae" |
| }, |
| { |
| "dataPath": "params_shard_360.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.58.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "84d389b730bc87ff6f822571d20b0a24" |
| }, |
| { |
| "dataPath": "params_shard_361.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.59.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6781428fc0cd0c08f8972f94ed6c6ffd" |
| }, |
| { |
| "dataPath": "params_shard_362.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.59.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6e3f30671c17db8d718e813239d22580" |
| }, |
| { |
| "dataPath": "params_shard_363.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.59.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1a8417d206d644f7c0b6345d57f1a7a0" |
| }, |
| { |
| "dataPath": "params_shard_364.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.59.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1fa4db7863578e7b265a39ccb371aceb" |
| }, |
| { |
| "dataPath": "params_shard_365.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.59.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1c8fc18e0603ebd6c4e427b523a83c82" |
| }, |
| { |
| "dataPath": "params_shard_366.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.59.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "afae4e255a233a46fa5305138ffbbf8d" |
| }, |
| { |
| "dataPath": "params_shard_367.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.58.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.58.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.59.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.59.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.59.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "8405e2b75472ce4fc0472b2038efab08" |
| }, |
| { |
| "dataPath": "params_shard_368.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.6.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d956231e6cd6a41c7e1c6a11c80f0d25" |
| }, |
| { |
| "dataPath": "params_shard_369.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.6.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cdccf716fd081ed671a60a1ca8f71dd1" |
| }, |
| { |
| "dataPath": "params_shard_370.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.6.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d6220b6c574fd1997c09445af8cfcdf2" |
| }, |
| { |
| "dataPath": "params_shard_371.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.6.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8898447149b627a7bc8fda718db1ebe6" |
| }, |
| { |
| "dataPath": "params_shard_372.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.59.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.6.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.6.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.6.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "b560ec1bac18ea20bb185b75b0f53beb" |
| }, |
| { |
| "dataPath": "params_shard_373.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a90e81f5799b4f63374f96567f47962a" |
| }, |
| { |
| "dataPath": "params_shard_374.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.60.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c512bb776d4342c79473aad920d4dea4" |
| }, |
| { |
| "dataPath": "params_shard_375.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.60.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f53bb7b2f193f48e7ff32b8f84ad060a" |
| }, |
| { |
| "dataPath": "params_shard_376.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.60.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c08e76f76d8470f78d07580d5c155ada" |
| }, |
| { |
| "dataPath": "params_shard_377.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.60.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9b8416f48584877a9a0ca60f89bd9c03" |
| }, |
| { |
| "dataPath": "params_shard_378.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.60.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a85d61cd8ea577ba9cc6b2ef67a1d8c5" |
| }, |
| { |
| "dataPath": "params_shard_379.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.60.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "79a7bd605740756f085074c5e97c7286" |
| }, |
| { |
| "dataPath": "params_shard_380.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.6.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.60.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.60.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.60.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "d67bf9f47ff23c0c831920fab97daf94" |
| }, |
| { |
| "dataPath": "params_shard_381.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.61.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "600a84ad3b475afa007e353e088c9178" |
| }, |
| { |
| "dataPath": "params_shard_382.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.61.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "603cca67ee110f11b9ca9baaf253c1e0" |
| }, |
| { |
| "dataPath": "params_shard_383.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.61.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "81f7b5488aa25b02223a635cb72a545d" |
| }, |
| { |
| "dataPath": "params_shard_384.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.61.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "30cbbbabd87b04391a5322b8b33334d5" |
| }, |
| { |
| "dataPath": "params_shard_385.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.60.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.61.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.61.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.61.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "3f80ae41b35d2ab93d805c6c75a6803d" |
| }, |
| { |
| "dataPath": "params_shard_386.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.61.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a144d8167a32c7c5fd898a11e338a4a3" |
| }, |
| { |
| "dataPath": "params_shard_387.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.62.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a7f50ce3210721352d846a3307e09806" |
| }, |
| { |
| "dataPath": "params_shard_388.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.62.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5e3a3e05be40297e6a2d77fafdd4a95e" |
| }, |
| { |
| "dataPath": "params_shard_389.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.62.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "638734b37af29aa3c634668e89b8887c" |
| }, |
| { |
| "dataPath": "params_shard_390.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.62.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a69eecce60bfad89ffbff0cc7a018f97" |
| }, |
| { |
| "dataPath": "params_shard_391.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.62.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c971780d59e5e56881dc9ba372692561" |
| }, |
| { |
| "dataPath": "params_shard_392.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.62.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "46c68aa90d881f16788230af42e884a1" |
| }, |
| { |
| "dataPath": "params_shard_393.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.61.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.61.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.62.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.62.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.62.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "4b63e90a6e8fbc2c32de9d74daf3af99" |
| }, |
| { |
| "dataPath": "params_shard_394.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.63.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "639bd8d63b7fb0c3d815e998745946f0" |
| }, |
| { |
| "dataPath": "params_shard_395.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.63.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a99602b7e79a6cb27bce8654d71b3788" |
| }, |
| { |
| "dataPath": "params_shard_396.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.63.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3caecd065df3a3e5f6acf7b6d32e32cf" |
| }, |
| { |
| "dataPath": "params_shard_397.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.63.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0e730c3c9ba7727be1110bd34749792e" |
| }, |
| { |
| "dataPath": "params_shard_398.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.62.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.63.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.63.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.63.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "fe63d1837a892ab72a865d5ff0d02b68" |
| }, |
| { |
| "dataPath": "params_shard_399.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.63.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e7850d98ac041cf10c9384764545a467" |
| }, |
| { |
| "dataPath": "params_shard_400.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.64.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6766e7f7040a3ee205e87ea96db831c9" |
| }, |
| { |
| "dataPath": "params_shard_401.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.64.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fe25bf590920c624effd0c71fe52eb7e" |
| }, |
| { |
| "dataPath": "params_shard_402.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.64.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fcdec498d627ae1293ebc580bec35c49" |
| }, |
| { |
| "dataPath": "params_shard_403.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.64.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c4a01eab4f30399ea8a06c1045d36cf8" |
| }, |
| { |
| "dataPath": "params_shard_404.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.64.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d26f49cc7e147850a73e478d1ec1fac4" |
| }, |
| { |
| "dataPath": "params_shard_405.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.64.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "186ee96b84006c89b105ebe21a7ee4bd" |
| }, |
| { |
| "dataPath": "params_shard_406.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.63.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.63.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.64.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.64.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.64.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "d3d11b8830fde63c0bdb9eccddc40d89" |
| }, |
| { |
| "dataPath": "params_shard_407.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.65.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6e968976d2b914d689376aa76a528031" |
| }, |
| { |
| "dataPath": "params_shard_408.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.65.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6554389de42292652207f331ac93c5a5" |
| }, |
| { |
| "dataPath": "params_shard_409.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.65.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f6829079329d89fe16de6ca4923778ff" |
| }, |
| { |
| "dataPath": "params_shard_410.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.65.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "48abd17aad852bd4e8d50f0c263309a8" |
| }, |
| { |
| "dataPath": "params_shard_411.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.64.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.65.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.65.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.65.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "754c806d263f2e32c584bd8cefcf9fa9" |
| }, |
| { |
| "dataPath": "params_shard_412.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.65.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a377cc46612662da51c7ecf6a9943c38" |
| }, |
| { |
| "dataPath": "params_shard_413.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.66.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ac4fc362582660284ac83b185ba7b21c" |
| }, |
| { |
| "dataPath": "params_shard_414.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.66.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "908160e9e1e7773a766fb5f738a1ce61" |
| }, |
| { |
| "dataPath": "params_shard_415.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.66.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "aec09424f4824a0d21981f5ace8fd2a5" |
| }, |
| { |
| "dataPath": "params_shard_416.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.66.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "547b926b8bf76e93aa1b46cc17df9b6b" |
| }, |
| { |
| "dataPath": "params_shard_417.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.66.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "85a899d768c2d3015c4eafda8a8c1173" |
| }, |
| { |
| "dataPath": "params_shard_418.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.66.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "67ab21c4a0265e567162094c2061bc88" |
| }, |
| { |
| "dataPath": "params_shard_419.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.65.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.65.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.66.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.66.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.66.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "7024f856e8ffeac9adc6b97d209a30dc" |
| }, |
| { |
| "dataPath": "params_shard_420.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.67.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "172c5c9d55a06ebe372a1ceb94d10012" |
| }, |
| { |
| "dataPath": "params_shard_421.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.67.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0e6bd0ef73e5982d53cb636c0765c3bf" |
| }, |
| { |
| "dataPath": "params_shard_422.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.67.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cedca66aef8316044a37d315cf836355" |
| }, |
| { |
| "dataPath": "params_shard_423.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.67.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "bfcd7a343c86e0815c68f39b93ce8a73" |
| }, |
| { |
| "dataPath": "params_shard_424.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.66.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.67.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.67.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.67.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "6d2785fc0ba5b4a0a23dd5103e641303" |
| }, |
| { |
| "dataPath": "params_shard_425.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.67.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c806c591864ac2ac13914c792b0e2c3a" |
| }, |
| { |
| "dataPath": "params_shard_426.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.68.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0a916b637d6255e2a431252174618eb6" |
| }, |
| { |
| "dataPath": "params_shard_427.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.68.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c412b77c76d745d50c1d1b204e2a0f1c" |
| }, |
| { |
| "dataPath": "params_shard_428.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.68.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7230a0dbd5854715a913cbc4ba7c99a8" |
| }, |
| { |
| "dataPath": "params_shard_429.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.68.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "732cc70e71ce8d25f2361c14177443ba" |
| }, |
| { |
| "dataPath": "params_shard_430.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.68.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7c6ad25f89d0488e3a2c9df47004eeb6" |
| }, |
| { |
| "dataPath": "params_shard_431.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.68.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2d969ccf849185354abca1d08f4c4bc3" |
| }, |
| { |
| "dataPath": "params_shard_432.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.67.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.67.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.68.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.68.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.68.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "78bf174df7e8544fd9824b9455ac28a6" |
| }, |
| { |
| "dataPath": "params_shard_433.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.69.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8e58fa7cebcc29299271d70a65f37ad6" |
| }, |
| { |
| "dataPath": "params_shard_434.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.69.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f1057ce3d348a0eb21bdaada23f4121f" |
| }, |
| { |
| "dataPath": "params_shard_435.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.69.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c971ba8f351cec310bb148bb7a506a8b" |
| }, |
| { |
| "dataPath": "params_shard_436.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.69.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7ecb680839fbab8227d2116b5dda8597" |
| }, |
| { |
| "dataPath": "params_shard_437.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.68.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.69.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.69.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.69.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "cf1f1c05733f4d96afb610e746a9d32b" |
| }, |
| { |
| "dataPath": "params_shard_438.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.69.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "232de9921f9ad8848121bd3ef5292e08" |
| }, |
| { |
| "dataPath": "params_shard_439.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.7.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "117128cf20a958db0dd13acb3f0edf80" |
| }, |
| { |
| "dataPath": "params_shard_440.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.7.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0475da58de86882983483a16cbed6939" |
| }, |
| { |
| "dataPath": "params_shard_441.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.7.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0c98bd5cb7ac9960fe613ab3584edb0e" |
| }, |
| { |
| "dataPath": "params_shard_442.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.7.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9a302b024490aa0f115a16d7e9e33f59" |
| }, |
| { |
| "dataPath": "params_shard_443.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.7.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7f0a3c2dd79f1d0c5d41c28a77d2c277" |
| }, |
| { |
| "dataPath": "params_shard_444.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "356e0f8002f2fea64cdb3c02be3754de" |
| }, |
| { |
| "dataPath": "params_shard_445.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.69.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.69.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.7.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.7.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.7.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "818755c67c0723d052f1f6dfcf43949f" |
| }, |
| { |
| "dataPath": "params_shard_446.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.70.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "11370b7034e2183892366e1c9906ef81" |
| }, |
| { |
| "dataPath": "params_shard_447.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.70.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2a46346f2a6df30f9a0f1d922a4393ac" |
| }, |
| { |
| "dataPath": "params_shard_448.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.70.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3b0bb948705dedfe83e64f2d1c10a840" |
| }, |
| { |
| "dataPath": "params_shard_449.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.70.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "156da6f18f2941afd48dd83a42c7d064" |
| }, |
| { |
| "dataPath": "params_shard_450.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.70.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.70.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.70.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "b9588750f37c766cf461860ecddd984b" |
| }, |
| { |
| "dataPath": "params_shard_451.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.70.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d63b5a990d71c582110340f0388ba875" |
| }, |
| { |
| "dataPath": "params_shard_452.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.71.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "bc156e9efeb56a84d131b2ab2239a2de" |
| }, |
| { |
| "dataPath": "params_shard_453.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.71.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2e7211a30f6783f6a086fdd5f60b2ee8" |
| }, |
| { |
| "dataPath": "params_shard_454.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.71.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1a258818677910274da9465e7140f387" |
| }, |
| { |
| "dataPath": "params_shard_455.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.71.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3e8d781491d264db620be6d07ae495f9" |
| }, |
| { |
| "dataPath": "params_shard_456.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.71.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "98cab1638ab049a01d5ac64d1bfa1e54" |
| }, |
| { |
| "dataPath": "params_shard_457.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.71.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ccb0e95e6b6d1de5b1d30d53d4f65905" |
| }, |
| { |
| "dataPath": "params_shard_458.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.70.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.70.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.71.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.71.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.71.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "962bf5897dda09f127283a4981047be9" |
| }, |
| { |
| "dataPath": "params_shard_459.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.72.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "879d56d8a143bdda0f8f2b25b70b23df" |
| }, |
| { |
| "dataPath": "params_shard_460.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.72.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b8cd6932af10accc37ced1277fe1ecef" |
| }, |
| { |
| "dataPath": "params_shard_461.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.72.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "694983cc4ba09b5950a9f41e6ede7aee" |
| }, |
| { |
| "dataPath": "params_shard_462.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.72.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "89dff5b78107cf4f32252413c6d2ea99" |
| }, |
| { |
| "dataPath": "params_shard_463.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.71.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.72.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.72.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.72.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "a5377f996cebf43ba83c577fd4a75489" |
| }, |
| { |
| "dataPath": "params_shard_464.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.72.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "33f9930aa7c9821ff8d97ffa25c401e0" |
| }, |
| { |
| "dataPath": "params_shard_465.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.73.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2c98fe8cfe4a2ab74326f0d0ec9c96b5" |
| }, |
| { |
| "dataPath": "params_shard_466.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.73.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "74dbe88645930313a10d85d1751a29ce" |
| }, |
| { |
| "dataPath": "params_shard_467.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.73.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "062f12137c5f58619b14e7778bbc331a" |
| }, |
| { |
| "dataPath": "params_shard_468.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.73.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5cca84c9aec806311f91df13eb2ae2a0" |
| }, |
| { |
| "dataPath": "params_shard_469.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.73.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c1e1e63d75af7a145189a5009ad34fcc" |
| }, |
| { |
| "dataPath": "params_shard_470.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.73.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b0407dfc5cf567cebd7814c063362476" |
| }, |
| { |
| "dataPath": "params_shard_471.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.72.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.72.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.73.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.73.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.73.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "c0d5e5c94fa3b73ebce4842ae36efb47" |
| }, |
| { |
| "dataPath": "params_shard_472.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.74.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4b27c07f18ebc653a7a1c8fa523ed433" |
| }, |
| { |
| "dataPath": "params_shard_473.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.74.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f4f1b19d8e90f6752d0462cfbd5e5fe6" |
| }, |
| { |
| "dataPath": "params_shard_474.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.74.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f3db31cbe0065386b20cdba7063c39be" |
| }, |
| { |
| "dataPath": "params_shard_475.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.74.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f702ed083f5e7ec096d28d17d4bc552b" |
| }, |
| { |
| "dataPath": "params_shard_476.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.73.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.74.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.74.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.74.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "66904a4f5891a29fba7dc1d6714e364c" |
| }, |
| { |
| "dataPath": "params_shard_477.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.74.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6cc501e09dfcd057ea8035a81cd02136" |
| }, |
| { |
| "dataPath": "params_shard_478.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.75.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3de9bcc606b90d634ba875c990b3b330" |
| }, |
| { |
| "dataPath": "params_shard_479.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.75.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5a951b5374512fc3f36dcbaba7b7fad4" |
| }, |
| { |
| "dataPath": "params_shard_480.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.75.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8fab3e83d9d92499166246efcdce37ca" |
| }, |
| { |
| "dataPath": "params_shard_481.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.75.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a8ce28d7bae97e9cb899f74127cc6232" |
| }, |
| { |
| "dataPath": "params_shard_482.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.75.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "56bccac2a1fca535dd2b79c5150b0259" |
| }, |
| { |
| "dataPath": "params_shard_483.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.75.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f4b5869d8eb47dd16487db1d788cd125" |
| }, |
| { |
| "dataPath": "params_shard_484.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.74.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.74.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.75.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.75.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.75.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "1438e139776398bb2aad0769c62810a8" |
| }, |
| { |
| "dataPath": "params_shard_485.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.76.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c62a30470404b5a6a06d598b4e931f0b" |
| }, |
| { |
| "dataPath": "params_shard_486.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.76.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7779b30c0417b59bab68a5e796f9e05d" |
| }, |
| { |
| "dataPath": "params_shard_487.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.76.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "15a8e8d770c448f9867f016e15bcebb7" |
| }, |
| { |
| "dataPath": "params_shard_488.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.76.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1eacd85d3a5ab1600d237aa53ca730f5" |
| }, |
| { |
| "dataPath": "params_shard_489.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.75.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.76.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.76.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.76.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "130d67e559555298140296fe8a1c75b5" |
| }, |
| { |
| "dataPath": "params_shard_490.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.76.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "068a121288aca137843b64019f7f9811" |
| }, |
| { |
| "dataPath": "params_shard_491.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.77.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8db4a778b9e34c75b89fb6cdca512e50" |
| }, |
| { |
| "dataPath": "params_shard_492.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.77.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1eef64fec86183b23dcea835973ef276" |
| }, |
| { |
| "dataPath": "params_shard_493.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.77.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7a178c58785ebc62b271a96ed3ff106b" |
| }, |
| { |
| "dataPath": "params_shard_494.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.77.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a78ab573b9a2af5e8a43edf0f4bdd67c" |
| }, |
| { |
| "dataPath": "params_shard_495.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.77.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "119a7ef0e2751b21d7ab05e18e54ac3c" |
| }, |
| { |
| "dataPath": "params_shard_496.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.77.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8c4928f84723cddaa91d623e3332ca3a" |
| }, |
| { |
| "dataPath": "params_shard_497.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.76.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.76.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.77.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.77.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.77.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "1e866eee47571535c2146dbde78f8c4e" |
| }, |
| { |
| "dataPath": "params_shard_498.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.78.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f1dcf3368b7c7d3d3d5cceee639cabb7" |
| }, |
| { |
| "dataPath": "params_shard_499.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.78.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "746a084d5c2ac49ad46075fecf9d8ddf" |
| }, |
| { |
| "dataPath": "params_shard_500.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.78.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "87636a84db71aa5fcc200ee958289935" |
| }, |
| { |
| "dataPath": "params_shard_501.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.78.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8238446162726e81de8bfa080016db66" |
| }, |
| { |
| "dataPath": "params_shard_502.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.77.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.78.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.78.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.78.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "84a2c27ba8cc85f4ef7d14b638a85500" |
| }, |
| { |
| "dataPath": "params_shard_503.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.78.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2c4b512a250953376d46e56b8905e87f" |
| }, |
| { |
| "dataPath": "params_shard_504.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.79.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b2e2a67f171ac152a174d162cd429793" |
| }, |
| { |
| "dataPath": "params_shard_505.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.79.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f3775235a54a0f3f029afa8cba10f2b7" |
| }, |
| { |
| "dataPath": "params_shard_506.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.79.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "742ba0b0778f7e9f8b0dccf3770426d7" |
| }, |
| { |
| "dataPath": "params_shard_507.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.79.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "05f7e5e249c680f72477fb16cdbd5c1b" |
| }, |
| { |
| "dataPath": "params_shard_508.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.79.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d13946f2dce444ab7fbbb873517b70f0" |
| }, |
| { |
| "dataPath": "params_shard_509.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.79.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cba53cf3532df9047b11976e53374c1b" |
| }, |
| { |
| "dataPath": "params_shard_510.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.78.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.78.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.79.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.79.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.79.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "b20cdca7efcd552443457815698a736e" |
| }, |
| { |
| "dataPath": "params_shard_511.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.8.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "179063ce6c6e56db4ed86474f7543d79" |
| }, |
| { |
| "dataPath": "params_shard_512.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.8.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6ef7d3dd83a3aa6a27d101bb5c6314f6" |
| }, |
| { |
| "dataPath": "params_shard_513.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.8.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "423b3c867c7e712a054b926ac8c56567" |
| }, |
| { |
| "dataPath": "params_shard_514.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.8.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "bd0d405b396e508a3ab9cd44547b8d03" |
| }, |
| { |
| "dataPath": "params_shard_515.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.79.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.8.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.8.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.8.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "5f5b879cdf546b4231357e3aad408ee7" |
| }, |
| { |
| "dataPath": "params_shard_516.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.8.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8712db89a284afe5cb9a06a5e4424eef" |
| }, |
| { |
| "dataPath": "params_shard_517.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.80.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "08bb139a88d3469daa2c66d9ce019dd0" |
| }, |
| { |
| "dataPath": "params_shard_518.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.80.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5d5fa21834ae4b3e0f8a269c80756870" |
| }, |
| { |
| "dataPath": "params_shard_519.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.80.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "79bc140f5b069ced89d1702807e8114f" |
| }, |
| { |
| "dataPath": "params_shard_520.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.80.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "679cc8fce9d93465403ab712aaa7287e" |
| }, |
| { |
| "dataPath": "params_shard_521.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.80.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5e7a7b519b4b365aa8bd201ea39c7ee7" |
| }, |
| { |
| "dataPath": "params_shard_522.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.80.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "18bb02e1afa51308da5fac169942a386" |
| }, |
| { |
| "dataPath": "params_shard_523.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.8.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.8.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.80.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.80.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.80.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "dd416c329915625c0a2a4086eccbf74b" |
| }, |
| { |
| "dataPath": "params_shard_524.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.81.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "55318946af3f1c82772b437205753f9e" |
| }, |
| { |
| "dataPath": "params_shard_525.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.81.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d358fcf4cea8144b8a162013b417c5aa" |
| }, |
| { |
| "dataPath": "params_shard_526.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.81.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c0a3e839053a5b4223b7617be542376b" |
| }, |
| { |
| "dataPath": "params_shard_527.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.81.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e508de8747909180fa4b7d2b9fa28655" |
| }, |
| { |
| "dataPath": "params_shard_528.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.80.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.81.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.81.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.81.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "762dba40e7f0e1ad9b083cb58a74786d" |
| }, |
| { |
| "dataPath": "params_shard_529.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.81.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "92340c61ffcebd0901e1cffb916dacda" |
| }, |
| { |
| "dataPath": "params_shard_530.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.82.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6861bef15bac51fadb47c1a0742dd439" |
| }, |
| { |
| "dataPath": "params_shard_531.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.82.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7345c43f60b29240a9d1f1bb8fd799f5" |
| }, |
| { |
| "dataPath": "params_shard_532.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.82.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9cf8f60e771c6becb48c3fb96a0700cb" |
| }, |
| { |
| "dataPath": "params_shard_533.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.82.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b0499d9b80989a5bcd2239fa98f4f6f4" |
| }, |
| { |
| "dataPath": "params_shard_534.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.82.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c9525a51a8a1da8535f38506ebb9ae99" |
| }, |
| { |
| "dataPath": "params_shard_535.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.82.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b61238f665e201b7d569523cde6283f7" |
| }, |
| { |
| "dataPath": "params_shard_536.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.81.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.81.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.82.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.82.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.82.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "448b932fff2b5296c04c5c8d7ae7865a" |
| }, |
| { |
| "dataPath": "params_shard_537.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.83.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "724d9bf4cfdc25ab36d91d6149fcb05e" |
| }, |
| { |
| "dataPath": "params_shard_538.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.83.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5312287e174c8fca2005e28f9b1bfe68" |
| }, |
| { |
| "dataPath": "params_shard_539.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.83.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "fcea6985c81404384d5273610bc45dc8" |
| }, |
| { |
| "dataPath": "params_shard_540.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.83.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3b62a9a7cfed2e1375af0f0875d73f5d" |
| }, |
| { |
| "dataPath": "params_shard_541.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.82.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.83.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.83.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.83.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "674febc6dcee2526f3e27759ad823996" |
| }, |
| { |
| "dataPath": "params_shard_542.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.83.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7ef28ad3d0081e6c1e746adeff3f4222" |
| }, |
| { |
| "dataPath": "params_shard_543.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.84.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4bf22498dc4530eda338b76d1eab4d53" |
| }, |
| { |
| "dataPath": "params_shard_544.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.84.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a818947083956abb8f92aaf82d89246b" |
| }, |
| { |
| "dataPath": "params_shard_545.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.84.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c04d0b794081b4a7d1586f2aad200a09" |
| }, |
| { |
| "dataPath": "params_shard_546.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.84.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "25a0983aec811d137da8bd85dc67b31e" |
| }, |
| { |
| "dataPath": "params_shard_547.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.84.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4f7fcd745b57afa40bf71b13047e72d7" |
| }, |
| { |
| "dataPath": "params_shard_548.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.84.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "27b13e9aee6c6ace7dc2be46bacc8b02" |
| }, |
| { |
| "dataPath": "params_shard_549.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.83.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.83.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.84.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.84.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.84.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "b4cc39e9134535edf63548fe8ae5bcc0" |
| }, |
| { |
| "dataPath": "params_shard_550.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.85.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "732a8d0f92080b7a48085042a0a2ccfb" |
| }, |
| { |
| "dataPath": "params_shard_551.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.85.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f7a0b0cadd7aae5f1d16b69b5531ea06" |
| }, |
| { |
| "dataPath": "params_shard_552.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.85.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "aab9bdf508d9b560ead54f6c06be9de7" |
| }, |
| { |
| "dataPath": "params_shard_553.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.85.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "014db9441ac87ec41f5d32dd884dc87e" |
| }, |
| { |
| "dataPath": "params_shard_554.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.84.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.85.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.85.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.85.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "a7d8855a3add232cc62db0741870454d" |
| }, |
| { |
| "dataPath": "params_shard_555.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.85.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8f5dd45d44b37976b19e211ef688f026" |
| }, |
| { |
| "dataPath": "params_shard_556.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.86.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ae8a2c2c13bc1ee388700642fa184323" |
| }, |
| { |
| "dataPath": "params_shard_557.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.86.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "aa454f1bc5425e0d171f6ed9c1459ab9" |
| }, |
| { |
| "dataPath": "params_shard_558.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.86.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5248c2acbf8e85338f1eb433abe73536" |
| }, |
| { |
| "dataPath": "params_shard_559.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.86.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1d6672e5156f6b3e42752d4951336235" |
| }, |
| { |
| "dataPath": "params_shard_560.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.86.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a020aeb0142fcb09a4a1d9e4a34aa2b0" |
| }, |
| { |
| "dataPath": "params_shard_561.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.86.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "02009183f97f1956e31c904172148bf8" |
| }, |
| { |
| "dataPath": "params_shard_562.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.85.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.85.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.86.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.86.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.86.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "329fb85071b4c9db595726cfbc59ba63" |
| }, |
| { |
| "dataPath": "params_shard_563.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.87.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "681c9a431d119ba0d35b2013f150383d" |
| }, |
| { |
| "dataPath": "params_shard_564.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.87.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "92b7f1eea41b9728290066b35acaab59" |
| }, |
| { |
| "dataPath": "params_shard_565.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.87.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2077a0c60f7ea478b943d940b6c7333f" |
| }, |
| { |
| "dataPath": "params_shard_566.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.87.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "64221dbe81e3ff120bf0ff5036a3f81e" |
| }, |
| { |
| "dataPath": "params_shard_567.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.86.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.87.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.87.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 9461760 |
| }, |
| { |
| "name": "model.layers.87.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 31481856 |
| } |
| ], |
| "md5sum": "de713779b8d6e11a4d962ab6bc10991f" |
| }, |
| { |
| "dataPath": "params_shard_568.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.87.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b01127b9aec8b0e2d84475f517f5d157" |
| }, |
| { |
| "dataPath": "params_shard_569.bin", |
| "format": "raw-shard", |
| "nbytes": 176160768, |
| "records": [ |
| { |
| "name": "model.layers.9.mlp.down_proj.q_weight", |
| "shape": [ |
| 12288, |
| 3584 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 176160768, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "89c20188b21289ca9fd3c158c42813d2" |
| }, |
| { |
| "dataPath": "params_shard_570.bin", |
| "format": "raw-shard", |
| "nbytes": 22020096, |
| "records": [ |
| { |
| "name": "model.layers.9.mlp.down_proj.q_scale", |
| "shape": [ |
| 12288, |
| 896 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 22020096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5060f789fb7bb7d69d37a31268ad7633" |
| }, |
| { |
| "dataPath": "params_shard_571.bin", |
| "format": "raw-shard", |
| "nbytes": 352321536, |
| "records": [ |
| { |
| "name": "model.layers.9.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 57344, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 352321536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0867cd945f607f297c30ae4b1ebb7d1a" |
| }, |
| { |
| "dataPath": "params_shard_572.bin", |
| "format": "raw-shard", |
| "nbytes": 44040192, |
| "records": [ |
| { |
| "name": "model.layers.9.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 57344, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 44040192, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "839ddb2f7d02b721fbd5cde554d56f35" |
| }, |
| { |
| "dataPath": "params_shard_573.bin", |
| "format": "raw-shard", |
| "nbytes": 88080384, |
| "records": [ |
| { |
| "name": "model.layers.9.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 14336, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 88080384, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "0a3c7c7bf35af7a138900616cc294cbd" |
| }, |
| { |
| "dataPath": "params_shard_574.bin", |
| "format": "raw-shard", |
| "nbytes": 75497472, |
| "records": [ |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_weight", |
| "shape": [ |
| 12288, |
| 1536 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 75497472, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "daa1661470490094be4ec1504d372319" |
| }, |
| { |
| "dataPath": "params_shard_575.bin", |
| "format": "raw-shard", |
| "nbytes": 31506432, |
| "records": [ |
| { |
| "name": "model.layers.87.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.87.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.9.input_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20447232 |
| }, |
| { |
| "name": "model.layers.9.post_attention_layernorm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 20471808 |
| }, |
| { |
| "name": "model.layers.9.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 14336, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 11010048, |
| "byteOffset": 20496384 |
| } |
| ], |
| "md5sum": "34a7f8beabd0eaa355b396ed07337556" |
| }, |
| { |
| "dataPath": "params_shard_576.bin", |
| "format": "raw-shard", |
| "nbytes": 9461760, |
| "records": [ |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_scale", |
| "shape": [ |
| 12288, |
| 384 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 9437184, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.norm.weight", |
| "shape": [ |
| 12288 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 24576, |
| "byteOffset": 9437184 |
| } |
| ], |
| "md5sum": "c3df0c554e4a2df499fd06380cbc328a" |
| } |
| ] |
| } |