{ "metadata": { "ParamSize": 709, "ParamBytes": 16895535104.0, "BitsPerParam": 3.0067237203635373 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 389283840, "records": [ { "name": "lm_head.q_weight", "shape": [ 640, 152064 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 389283840, "byteOffset": 0 } ], "md5sum": "fc6101d4aec293d4610b4d061da07594" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e3029b403f8ece245608f6fd480de38b" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "6251fa918295a16ec39c6f675af30e13" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 389283840, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 152064, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 389283840, "byteOffset": 0 } ], "md5sum": "2160f6cbda407f70c0d2058e2543e6e5" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8844ae2ef8aeac282075495f0ed33cb9" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "466915118d0035dc1649e89e311914fb" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33218560, "records": [ { "name": "lm_head.q_scale", "shape": [ 40, 152064 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12165120, "byteOffset": 0 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 12165120 }, { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 12175360 }, { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14387200 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 18810880 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 18821120 }, { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 40 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12165120, "byteOffset": 18831360 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30996480 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 31006720 } ], "md5sum": "f91d69acede10f5069c1ceec22342abd" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 23371776, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 4423680 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 4433920 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 4448256 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 22798336 } ], "md5sum": "7383675dfe8f71f4b718fef03498e0e8" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e2e01354a688dc69f8144cc0e2a268ed" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "d8414fc01cf2aebe2124fe531d8563d7" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "edbe983cf5fb116f5be4df9c868778ed" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "3b003259ed167af39e45cff2ecd46592" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "381173d6f04b99b9140eee619248b581" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "fe4863acc0076e0200554cb6070eda24" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "bad07eb8706c833098a03ce01d9ffa37" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "01846d1902ae7ca82cb575e42ca4c951" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4bf42bf914ea38476af2bf2b9d6b762f" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "362f9f9224dc5db70db690a911d97048" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "07822c54f1aed36a312b326a661666aa" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 32055296, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17940480 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 17954816 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 18528256 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31635456 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32045056 } ], "md5sum": "92018761d25fba4857242764441cd44f" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9c4d43d032402f3412146b9d21ec0010" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25583616, "records": [ { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 2211840 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 6635520 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 6645760 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 6660096 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 25010176 } ], "md5sum": "15d17fa70d1469aab8d0ca814721f165" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "988d076db6de14f6f71de7eddae1963d" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "3922e04c8099dc2a7075d003e453338c" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "662da3b189700e3f6a1850c46b907c31" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "7cace7da99ae4fe2ac47a650be6a572c" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "683d56211627e8bc5292f446d0039fbd" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "3eb284760c8ab67c03ba7872927e84bf" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "11542ff5bd184d9bc88998e0ac220ed2" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "dfd1bdc1c0710e58e0e858d94ac936c9" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "f283d6b9f469cdca977ef1160fc730c4" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "0d088f69da0b55b7b6b4102bea507a5e" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "bc87ff9836809dfbbc2e0dc618dbf41c" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 32055296, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17940480 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 17954816 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 18528256 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31635456 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32045056 } ], "md5sum": "3a6496625450bde8c2cac4e67d515921" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "17729c992e5d0c75b594ed819d3a9e82" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "32fa7b08f70b062813d95170945fe5ed" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "1313cfbe3d5d279c89aab78c7dd81113" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 32239616, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 2211840 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 6635520 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 6645760 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 6656000 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 8867840 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13291520 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 13301760 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 13316096 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 31666176 } ], "md5sum": "01bfdb70a06089856f6465df9cf91053" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "28c130303062e13e9867ecdd273eb520" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7401f32cf3624495c47489239bf75c1d" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "6b6c6b2fab9e5e52f97a5abe84ae62e7" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "63a34bddc82ebee5302ca458e30eac6a" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 22992896, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 15738880 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 15749120 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 15759360 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 17971200 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22394880 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 22405120 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 22419456 } ], "md5sum": "fa4aea231d7ccc2009b2b6ce33624c9b" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f83d520af6f7dda426db47d22783e2ac" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "c7e045e595760a3b0484cf66f1406a0c" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "521a56971691e214b9ca90faeaa637e4" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "315e1edcc7b5b7abd60422187c96a975" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4d316f6b7c4644233d0ae6b23a89c13c" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "27d14b4b1d1e31e97aafd59545dff15e" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "8f935992ddb22b29ac33e290c1536925" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "4ddaa2f69d23f3faf88893599e9e93b9" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "08da806435deec8ff1d7e866c1c4f4ad" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "3048f78d24e69335a8d994ce329b5d04" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "11a99023b95cb793968b219128a1a1ff" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "67c62420bbf6f33f6e47652d1a962764" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a5ad2932b54e3873c02d585bd674ec19" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "d08d9715ce7f7e2dd27a32a5b488f7d0" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2d5a7414d9469f88bd484ec914a635c8" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 32055296, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17940480 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 17954816 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 18528256 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31635456 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32045056 } ], "md5sum": "ec57956f5a761c7f62644ed964e01897" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c782079863df2936fa99e2da86a2e125" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "63c0104d3a6f43c3cd30816c7bbc6a27" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 27815936, "records": [ { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 0 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2211840 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2222080 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 2232320 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 4444160 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8867840 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8878080 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8892416 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 27242496 } ], "md5sum": "44c737c41552b5840278561025dabaee" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5c9b857dbfcc0c86dfe2aa99f25bc7be" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9b9efc1e7b2ceec4ebb366343d5af16b" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "98ec1b9bdc2e3d9c1b9f4d16971a9557" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "5de32d1e2161fa0c487a032f6a786422" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "42fff9f4b4169b66386f58a8d6de69fa" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "047bdf25ae1e8b9718bc6e9fa86899a2" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "0e6ba674b2fff585ca0bfe4779be6af8" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "ccde50605f7576c1147d424bbcc5bb6f" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c153b39eb9ada1b9389bc41c317d1799" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "78731ab6fbec3f26bad932349aa0cec8" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "cf045d54a2014f068b081ad85e18a854" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "91a835020a791176b88354448f7887ad" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "e5dea608897e260609eab7bb82285f00" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ec5a3b1dc1862b735699ed56e2ef299f" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "3e25602a271fd102178f2b94d14ce13f" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 32055296, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17940480 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 17954816 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 18528256 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31635456 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32045056 } ], "md5sum": "94c15eedebd3eff48cee9ec399b45568" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "fb3674c4dba50828c0830fe36c20d21c" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "f6a2ba3d6835adb7cb7e85705ee04f7c" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 27815936, "records": [ { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2211840 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2222080 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 2232320 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 4444160 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8867840 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8878080 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8892416 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 27242496 } ], "md5sum": "e168d1b80462be24b26100aaaf178899" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "670d984eaf51b058981c193efae73ca0" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "17c8f5f45151656ffc852e3ac4c3bf70" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7415ef306a89ac3a5dbd4d5d669e678e" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "290927ada0443bee687d39036b78e215" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e2d1bf3e97013975554b2d74f61b46d3" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "5491dbd37b53c5bf23b22d7bf82bb3c5" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "1eb7670f0a32bc6e3dd0c704b45f869d" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "8061dfa5f81003fd8cf4d686f91f2ec0" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "146c0e71657c8b8f4494b70bcf052f0a" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "5a67715366b1d82baef21f3a72eda440" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ad5e508109a7e01c2017143a27f274b2" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "f1b2b908ddfa86475f9f5ae710d45b01" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a154577a8250951a37677382d01ad8ec" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "de71cce067a02ca0ada37818d8f27666" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "223dfd63fe54f30df6b07b41f697806e" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 32055296, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.28.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17940480 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 17954816 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 18528256 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31635456 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32045056 } ], "md5sum": "f93b71fb4311e4060f196a495a200b36" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c00608fda13cd10f654215798d88e4ac" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "1d882d2eff186a652276ffa990c15e7b" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 27815936, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2211840 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2222080 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 2232320 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 4444160 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8867840 }, { "name": "model.layers.29.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8878080 }, { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8892416 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 27242496 } ], "md5sum": "ebeb8f46fc869a6abbf7b89a55763ddf" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "916308043a1763a5e83d36a8db0f3765" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "981b0845839d3fd7098cd49bda85e0c9" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "1248900a5594913295e8afff88097682" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.30.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "1284aa6448ebe6f018e895e2cf7c55b5" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "521c70b05f84d659a335fe56655921f0" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "ad4de251162cf9a61f4f816afc6ca4de" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ec2379b078f28200a6f640640aac2c12" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.31.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "c0427aaa3a070e861c0bbcc103bca61c" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ec0e8ea926bbb26541e6dd0e3b77714d" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "71f41c693cefa3f6e85166fc9c891f6f" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "9bf243f4e924bf234f3406b81a8aa1e4" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.32.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "9db73f691f03ec47235d11b23ed2db5c" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "91c29af436e345b2a987688dfa26a410" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "9138cae9f76dccb17b826ef39704e992" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "499bf327e448962f0ae6d62d7f9a4ba9" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 32055296, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.33.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17940480 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 17954816 }, { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 18528256 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31635456 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32045056 } ], "md5sum": "4e0cd3413a73ce538428ed16ae5dcb31" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "bf50c050fbf987ec5b5593e1dc945a49" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "bbb90e25017cffbe18397efa855b7d00" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 27815936, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2211840 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2222080 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 2232320 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 4444160 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8867840 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8878080 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8892416 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 27242496 } ], "md5sum": "6000b0c60e780281df0a5350d1bb52b8" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e29fd3a940b09cea9e30a64371bc6fc1" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "508df8e94b36089c6adaf09e6f5c18b5" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "6ae263c3fe7d2287c1a199e28f7254eb" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "37a2d4f64852b8ec663351859fdbbe27" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "35dce17591aa7e72735ff1dc72b0fb0d" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "5183ade84b789b368c3cb6aee59018d0" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "9d44cdca45298fef35ae91ab4bf7aab6" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "1101f01fa1dca18d999c610517fc1be5" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2df0bdd1dbb4e38f3af7a7e41d78e994" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "566c7ca28e2fb564c83c026d2d712280" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "5327d4c2b80201097e105468cf1818c2" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "2555648e42a1e949e2f6118dca592b1c" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 32454656, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 13516800 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 13531136 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 31881216 } ], "md5sum": "18923dd8c542d137719350cbcac7c729" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6faac75761f59c59dd2860962cb0ad85" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f4f6ded7e72f781b5b6e630cbeab90ed" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "0b2c642f4d29d17540a636b2468a432c" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "9d1cff8f23803b5bf5a2b794531292ef" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 22992896, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 15738880 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 15749120 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 15759360 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 17971200 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22394880 }, { "name": "model.layers.34.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 22405120 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 22419456 } ], "md5sum": "48f89a878ff6ca729e651bf6ab17882a" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "fd078c33f9b10be6663cc8e88dc3b51f" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "f0c3a2787643f74b5cd4c6062f2736ba" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ef1d2b2d08351939eabc8d46b68c4085" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.35.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "d54c5973f42da61423c72ef6ca8a3677" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "55873604ed6f7170786b160e30fb00d2" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "f440cba338f668801935d6a872854998" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.36.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "d70f5dd0492484749a0ad83d7795e080" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.36.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "138c126ef8392974916c230562cfd0a8" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "bb31e974f3cafa0faf397aec69732738" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "bfdd594b2e0b527009deac3ee7de651b" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.37.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "38becfa913846fd05a71920cd7be6181" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.37.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "689fe9e772d795e3065cfe7f2cfffc63" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "7a17957cb133a0a9a18bc03ec00148e2" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.38.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ed1167fa78759dfddd7b6f0c9aa36aec" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b5b2c5d00842603a409efabe6efb9ef8" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 32055296, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.38.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17940480 }, { "name": "model.layers.38.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 17954816 }, { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 18528256 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31635456 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32045056 } ], "md5sum": "6874980f9ed2f4b4a98c46bbef52686e" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "0f5139342bd2330181946069bad8932e" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "8053c02def42e8329962f485121c0784" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 27815936, "records": [ { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 0 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2211840 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2222080 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 2232320 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 4444160 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8867840 }, { "name": "model.layers.39.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8878080 }, { "name": "model.layers.39.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8892416 }, { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 27242496 } ], "md5sum": "f6a80fa5d410f79d2ee28c827e76f389" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "0ffd0ea2b99710726241018e2e1f59dc" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "c814f1f6e192ed8d9e024519acb20f00" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.40.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "edb3e29b389d73b46d0e5d2382163dc1" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.40.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.40.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "f0fad7c3873216f6e109acba9d6167e2" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a1642231b268c799d2e2b8d827bf8a18" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "5d58fd8f7fcb7eef70f44550c135f444" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.41.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "46aad16dd5aacab50f6b2a119bf9b357" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.41.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.41.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "87549932b108075a97f6c6600124a623" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "9edb9df9ccbe71e35bea94aa9c63abfa" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "94041b740cf313126f16564e027d6f8a" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.42.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "3c2ed43ba647fed62a4f3e6f066509bc" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.42.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.42.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "f2e82eda706144228417019f2f0730ca" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "efdc5883e6796a86c7777f51cc413a6a" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.43.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "d81e5fa36d4e5f33894338bb4a7cbbf3" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e0321674f40dcdd3a3301ac27bd19442" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 32055296, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.43.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17940480 }, { "name": "model.layers.43.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 17954816 }, { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 18528256 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31635456 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32045056 } ], "md5sum": "d94f6f874d7037c885f94bbb6796a549" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "55069dfd52ef66b194940c4bb40ed14a" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a8ce2b3692ea88b7d8aa7ee447ce6144" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 27815936, "records": [ { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 0 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2211840 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2222080 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 2232320 }, { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 4444160 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8867840 }, { "name": "model.layers.44.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8878080 }, { "name": "model.layers.44.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8892416 }, { "name": "model.layers.44.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 27242496 } ], "md5sum": "fc988b62e74e5291f380189b3e04c7fb" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "17a797a52dd9aedefa4034fc7d115e14" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "2eb13721c280554e2d2af5fea56ad871" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.45.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ead8b46ffd2d96bbad5f483bb6d6a2fd" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.45.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.45.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "0ff3b2fa1a4a32a755a1e067aa061966" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6744dd21845a6c09eb6607c3de0c4ade" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "d39bd04c8e650246e0343b391d2d2fdf" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.46.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "a9cceef1c4f10b80a0e577828b98b9e2" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.46.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.46.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "015b630dd5d658a5bc4b9e8e81eb9705" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "134f8f08eb2eab9cf23726968dd63254" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "667fedcaacd7d6601b91d8024a6a5c03" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.47.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f6458ebf3084f7191825e839e8b45ab4" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.47.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.47.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "11ec0bd12937d82e754bb0bad994719f" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "1d164a2f767ec826ef0b66fdd04194b6" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.48.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "3d49fb6e87e37f9a63603a2c2e4362ce" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d617ca69e851ccf45af4b512a4586e18" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 32055296, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.48.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17940480 }, { "name": "model.layers.48.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 17954816 }, { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 18528256 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31635456 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32045056 } ], "md5sum": "014ee361c554f7112d2580ab0f857681" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6513d3e2ba8847ca0d8245f468304a06" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "846d3abb00a997cd2f8280419cef6479" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 27815936, "records": [ { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 0 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2211840 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2222080 }, { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 2232320 }, { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 4444160 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8867840 }, { "name": "model.layers.49.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8878080 }, { "name": "model.layers.49.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8892416 }, { "name": "model.layers.49.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 27242496 } ], "md5sum": "021a2d3be0453079e6a3193d8e80957e" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5be340d54a989e899e600b563b238ab6" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4ad2555277c722edd7e2b2dc1ecf135c" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.50.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "a0fd8a06bf5a867d9ae53b9fce99a0b7" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.50.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.50.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "7854ac85b852273233b0d2e6117e86e4" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "34b9d9349ddd8cf49808ffb7c6b075ae" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "c04fd035760c02f1c21799758412079e" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.51.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c3401689e6a2813fd6484e527bca9560" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.51.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.51.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "591d3e470695efee4f8fd27ca13a3a5f" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "3ca37a25b077b7bb334f3dc97a35d18a" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "2ca832d2e16d16a2c44ad237b4a16c99" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.52.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "a5437fd6f06c37f5679852a685ab7fd2" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.52.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.52.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "6f5307031bf9d45df5cb171d2635475b" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "54c5429583dede86649689ec2ab8b5b3" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.53.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ebcac004f10c100bd81659046d087bac" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a3b82dc091150d33d0449956bec14d97" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 32055296, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.53.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17940480 }, { "name": "model.layers.53.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 17954816 }, { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 18528256 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31635456 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32045056 } ], "md5sum": "41c2d499b44e41e0c460c4d3f7f1840d" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8782171263419ffcba792edc4716b929" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "53939b7a56c1a64c438be58b633aec46" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 27815936, "records": [ { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 0 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2211840 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2222080 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 2232320 }, { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 4444160 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8867840 }, { "name": "model.layers.54.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8878080 }, { "name": "model.layers.54.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8892416 }, { "name": "model.layers.54.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 27242496 } ], "md5sum": "07affe20381940744c7a4697e35c5285" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e1840a20f8f194bfda961cbc9556c4b6" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "d3df75be6263785d7c4a0060066d8eff" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.55.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "3a475b8411f5a4a528b176c45d7ef13f" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.55.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.55.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "17c5b1f6a98cbb6fd69b23da07384dba" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "043a418fd4741c6fb73e862c3ac3a333" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "25abdbeda9bca81c22e92349c047bff8" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.56.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "99799cde1f94b1723a1f74a66655424e" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.56.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.56.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "cd9a98f878bf05b0c349bc09792522d9" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6811140f8fd3c2ccfdc36cbd3635bb9a" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "fc3be65439600ae74cb0a8ad148ef0cc" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.57.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7b3ddcfb2f20215d3bd6196dbd4d94fe" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.57.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.57.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "22364da1a7abd47b678285ee5eb05e40" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "c174ec738dfb8456281737e006e469e6" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.58.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "325dfd8639cbb7fcc33d9c747440f3ee" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "fb09595adfbace3daac86f7f65f8ec3b" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 32055296, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13516800 }, { "name": "model.layers.58.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17940480 }, { "name": "model.layers.58.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 17954816 }, { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 18528256 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31635456 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32045056 } ], "md5sum": "7bcc8dae46dd1a0c30aab25a6d2b9dfe" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "42dbd9855c7349ff0253b5da8f57f92a" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "fcd4c5f19719666120a5b6ab3ad23858" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 27815936, "records": [ { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 0 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2211840 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 2222080 }, { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 2232320 }, { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 4444160 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8867840 }, { "name": "model.layers.59.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8878080 }, { "name": "model.layers.59.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8892416 }, { "name": "model.layers.59.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 27242496 } ], "md5sum": "c515e7873bf0b40ca571f8b11b6857cc" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "3cb562dddc89aaecff8818e2176f882e" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "72818e9acee43d6f5581e22c647b2712" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.60.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "e376fe84f1acb5863db9fad9e2870ba2" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.60.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.60.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "e8b028836a12b345652520f0a4bdbda5" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "27a09084fa70fa0676c1ec4f6acd43d3" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "245084597103e1bfeb97ebead6f66af0" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.61.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f56f62fcda0e9c92a0f4b705dca7b271" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.61.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.61.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "7d40707a0bc7b7ef2aadb6761aae7b7d" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 3456, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "aa1655cde65daa1a17d8602bc15016bd" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 640, 55296 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "607a18e0e585037ea20f1c9567b4dc03" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.62.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c995c8ceed104b5e58e1ff53ef944869" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 20760576, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13516800 }, { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 216, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 13527040 }, { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 40, 55296 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 15738880 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20162560 }, { "name": "model.layers.62.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 20172800 }, { "name": "model.layers.62.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 20187136 } ], "md5sum": "4100bd85a60b3be258b3607197cf7544" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 32454656, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 }, { "name": "model.layers.63.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 13516800 }, { "name": "model.layers.63.self_attn.c_attn.q_weight", "shape": [ 640, 7168 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 13531136 }, { "name": "model.layers.63.self_attn.c_attn.q_scale", "shape": [ 40, 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 573440, "byteOffset": 31881216 } ], "md5sum": "667983ae1fbe7494d55b39e2a7aaad75" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 13516800, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 640, 5120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 40, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 13107200 } ], "md5sum": "98b90c357be8fdb1592eab51568e1c17" } ] }