{ "metadata": { "ParamSize": 709, "ParamBytes": 20481200128.0, "BitsPerParam": 3.8538355688324186 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 389283840, "records": [ { "name": "lm_head.q_weight", "shape": [ 152064, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 389283840, "byteOffset": 0 } ], "md5sum": "15521ac51518b7327eb150c912cdfd95" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 48660480, "records": [ { "name": "lm_head.q_scale", "shape": [ 152064, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 48660480, "byteOffset": 0 } ], "md5sum": "400cdad8063a9c9612b26640b4e98480" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b13baa29ed4a1a4d260e16cc22753efc" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "89ad7297555dcd80f7e6b59eb355da4f" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ea53c3c395e1b74500c22c788bbffe71" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 26552320, "records": [ { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 } ], "md5sum": "9d329ded61c4f6cf9246f919df9ef0ed" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "80c1f2f2a0a77d87273455fde4684888" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.63.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "3cae8527f41caf9fc4cec0d3b4df5a36" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.63.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.63.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "6ef80489c819fed1ca1e1c9428265a62" }, { "dataPath": "params_shard_9.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": "ac65490ec912b245a739e5e6a787b2b3" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 48660480, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 48660480, "byteOffset": 0 } ], "md5sum": "7f3fa28fa5727a435fb5db5824a8d086" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "15fad14d4f7883367ad3bd339357567c" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "6aee84ab62978b1a963dcf1bb04aecbf" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "3733b0c0c4a4e0cea141099ec6e0af38" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "30c49c677879087a8d9be39f11836945" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 25931776, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14755840 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14766080 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23613440 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23623680 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23638016 } ], "md5sum": "18555a0a6389245ebf9e0f11f15b25bb" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "31e77e9748861e5d1c51c5b5746e0391" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4c2bf1761369adefc97d545186f7fcd2" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "4195ad961b2936396e1e1de41b6ad4bf" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "b07234a039710c6d8f7816a2cc6ea270" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "de69bdad27910eaf86e46342ddcd47be" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "1e510f5688fda1eeea4346d299eef0f0" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7ccd5c72df113074129385d5a7365801" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "87c1cd7796ea99453ae488769e313dbe" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "f2b35b518c5611bab954387230c29e67" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "0e1d0fdfb2a5dfab5201387c1570f550" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2e1c417723775e953574c93eecb73f3b" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 17039360 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 17049600 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 17059840 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 17074176 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 19367936 } ], "md5sum": "79875055efb57d8d23d4f1644b77f319" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "03ec0ea6fab3a47239955d6d46a44a85" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "d4ce9b7e4cda7647fb73632054f616c2" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6a1a71250ddb7cb3eda7732ac7b1c15f" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 28190720, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 0 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 1638400 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 10485760 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 28180480 } ], "md5sum": "160b535f2edea6f16fb4aeb598fdb3ca" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4543114dc1fde982a442b6a6014dbf17" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "9a4b07d8e809977f4feb0e0734b5c034" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "e4ae90e3c9890f59f5dff6f9e890e7c1" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "115258225375226ab161d841a415fc6e" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a689b7044ae583153d19b1706c23f343" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "959a8002225ba8ed59786693d3eee1bf" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "eb8a7001a30acd73421bddb8f4f22451" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "0d3e79598abec764270a778ffc20d009" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "004794139464e555a10158f266963fb7" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "efcc1951ffdb1482416929f9b3abe6cf" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "2215437512c4f523b7c9e9c539110024" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "9955299eab85c506b7f5007efca7ade7" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "cfeff25fe87dea461f349557717ff082" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4e3742b83b9ede6d26febc1c86523d7b" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6c76c64c02f1822f902d338ae1eac37f" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "3167187cd47e09f3980debdf3e625251" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "9a4d3092597a2cd211a6f66872d98603" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2b96ea6668b191f87279ad0516095042" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23592960 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 23603200 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "7ae53f60f2808ac864756d69d5925f68" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "24c483b54351a99ac6c7114f9b0ec3e8" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "31c269c9021698793faec796e1bf1e02" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "0f1279467a363620747690fad9997b11" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "373282209bb76f199baa5c8a207a1225" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 28215296, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 17039360 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17049600 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25896960 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 25907200 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 25921536 } ], "md5sum": "2ebb22104ad0e752d354e14d7b547841" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "61badaa01fcbfea80761a89bb5d912ed" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "dd8df543303ae83f39b80f0c7997636d" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "1969cec4a0d6aeed524213df203fb5f6" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "8894239d2489bb6883944fecdcf234fe" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "d2776ad19fc3ec24406e5b0f2a49983c" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "1ae4461b573f9d55d48c8f272250886c" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "1dbe115786d08ab445fa7d8685c44820" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "05328e551bb10c8d749799bb03e9bbac" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c4bf57b3306af4b1d58ea5662c46b5a5" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a7140d0184e5218b39e5caf136875354" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "4038d60749de9ffa515eea57f0911496" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "1ffa99f3f768100acac0c8bc80a4c7c8" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "218691de3b713bde1e159a065e275c62" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "74a84915ee49e59b8e8cf4755e19c9c2" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "feefaac61e5eba79b22948217321a823" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "3dc4a471bebcc7d679bf2d9b4401170c" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "7517b2f8ce25f0c9d1f01fc95cfd2a09" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "caf29ffa9a6c8efc6659239203c1b946" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "2015cb324420d6acc82fe34f476e21a8" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8674bc50087fe147c8d65accfdb69e31" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "2beb4a3ee69cfa1866ae42f4f72d2bd3" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "fe299d17a91a1224d2140a16c84a61b1" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c9f54357fcf3e20cfc06225fb871bd3c" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "93e299ce6cceeffeb9d9fc944022f810" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "99ad4764b6b1bf86fef70a9a5b6ae037" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ab79c49689bebb82ac6e0f941e938cc9" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "ab8ebc419b785572430d10bf4a8fc330" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "df30ce8222de96ec7d9f4b0727761a2c" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d993dc4e54db6b67dfde7aa8ae022214" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "464ff071b9633f82d8d2ffad77a65bac" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "f4c34a5df7c587c213db599ddac79e72" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "23f33e3da8e93731ca1037e9738a9870" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "b3407aa32176dfac9c75022e8349f75f" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f341ed02bc21289026879a6363f4b2bb" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "50bee69a4c3976846e88b5db30ee072d" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "2a272b7f2b79e987b1faef63a6b3b094" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "3554478b1d98244247929035cc374ff4" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "1fc52eadd09e46f884b0517d7e8b31ce" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e1c682989b901fc11775c0be624c1ec7" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "ca8c0b4b7bbc4db5e119a8cd6a33a9fa" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "278d8d4977aa3219fcb1647701e53757" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "cdd7103da20e4b6e9ffa9c0d52fdaa7f" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "2f41685e35ff89c0291584665f73d0a8" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "c8c890e3d4a224910bc5139242923f99" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "325106e39ab9a222fbc7bd9392c7269d" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "b59aee87fb05e2b14fd7ec86a9f795b7" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "08ccd3e60f7f060ceae69c705314e459" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "852e6a27dbc906dd9b96a3095c5186ca" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "01743f704094e6d0171a9c99a3a23fc0" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "2a46f70884cd4e5a485336032ec11362" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "01c35657d5acd88fefca650878ea92bf" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "e4768bd9e285270b40adc3ba49dbcaf3" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2dcffe336c8f367d1ddccac54100ac41" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "be68ad24f2dd2a412a734dc34ad938bb" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "003f5801a79d5cd050139d65d550686f" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f9afd2e2a7c0e13078d614e1e53baf3c" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "b0938f41e4971c2e2d9aca07c677bd52" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "399ed6ac29bff6997c6de22a48bbd1b6" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "511e51914a3de9cf96e025257619f63e" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "254312c0f3e2ddf085f5c92428f51c1b" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "e87097ecbe86ffb319ad7e952522a44f" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "9b08a8960eabbb162f4d1a2cb96a94a8" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 33130496, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14755840 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 14766080 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 14780416 } ], "md5sum": "26290e6202d6120f822c3204d097f481" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b3f5f6799de2281e1d7db561ddce3d1a" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "02b77d693410f17929727b1f1ec06654" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "ab69d81b90a91928f4c5b9792fb0e92a" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "056d179b4805eead4de94c987a872e2a" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7b9fde556d6db0fcc384147028e45195" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "37b13efd76bb39223e1f93acd68fc2c5" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "47ac7036fc0e5ed44655c403997b849a" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "b184729efe86aab01eb49d5d6c36a3aa" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "9f6352fbf41048c092a0354fba5d0f45" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f4afd24b8ce55a0c90cef1da7ff20877" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "579a2d3828de9cda49f2d01bf9baaa72" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2dcf46bffa4b921f2947746badbafe3d" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a1bbe1fe5b2bd33d8020456ba68e78ba" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "ec84c42daf8945c06bec4e9e9e6dad04" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "8b59ad020cb451497130e5727a2951cb" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "50effb986e41584ce54f2c35d0554712" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "e4665168d7aa8d6c8cd6278dc042f901" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "d123076c8b2b9d609540a35da6db23b9" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "65b0631159d3aff495fb711cd48837cb" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "30909cba9732afefaf140d276f920eeb" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5ecad5180e03d2a3c5d3c82a00cde91b" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "e2f085c0a3361b404a3f63bfd1767394" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9a39e3ba5859a35a1c41a7c8b93a63ac" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "504c944b48031d094690d8e2e6c98a82" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "dd693a4ebaea805ab5ff44ef9451e973" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "0277f54ce11f2e792f91ef842aace40e" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "b5565d0e87bc7f81dae94b263be863a0" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "54088fdbe7876664a84ffe042f269513" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "95a5ac5912103da5cbf21b4cd93618ba" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.28.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "7b5cf7d13cfdf900ef7e2b79db8d9616" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ced1d21d9ebbbc88301b5200dceda952" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "bea1a837014f732de50bfe755b97b675" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "de8bc1a384e499c9414e6d277697266b" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "e53b6f3d8321818919cf8c67b8d62caa" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.29.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "8a1d24b8d8b533c564449b5baa046753" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "ea8deaa24ca01ce0820e845212e73b84" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "fcc768faf9ed0d075d7b60b229ff2ba4" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.30.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "5f121c0d2a6ff9eb8d119683d86e4e3a" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e3fa54efaa5a675eaece64b60ac8e92a" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "42837711be8e65da76f42b3c102dc2b2" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "5c090403a271970696d47ff16c5daae9" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9c22da8fde6fff83631cf259751081cb" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "08e6c71ed1201e30ff41bfb0a2d80463" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.31.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "9347e0ee3d07578dec12156eb4258b5a" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4e5c967cdeb5b9f53552e9749a53b630" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "63f38da9cf53967853eca0a75bcba8cf" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "42093aaae445811b4244c09d592c191e" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "79fda5d75010bef2498bdbdcc35320d6" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.32.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "90bf3c0c38c4eee6e3d6d9519fa2709e" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ffe799b9b762466d4d3c6c10453ab213" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "f314669eb2ee91b7d369824afa7e0e7c" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "f02d822fd37b26d65ef47c2da4bd35f7" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "35693bb128a4722109648fda5e1dda8c" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.33.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "3574d67a9ef28da82631ae152e44c5c4" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "0cfb04edfd86b6c2a16b0ef0b427a575" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "29160b687fbf1a147c1d601737786f0c" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.34.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "d7ce32756e3b7d35ec6b47c1cf9cf8a8" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8d1c641597d1d7f7a89137dde9f51d22" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a512019beef3ff6cb23d2d1b78fab140" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "75a13ff55e96dd60e7a7da097d85d72c" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a1dad864475a1d323869ba4b0f4be0e8" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "3098858aaec54f65de434dfc0cd253dc" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.35.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "fce434c70de06cbaf3b5a5417a41f786" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "538c23b2bae55430fdfcdb224345085f" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "e3ae1b656d8ec528e8fe450ffc7a819c" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "66ea2a99923c945a34bbd30d39df04e6" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.36.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "99a57bc424c0d60974851f39d440c22c" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.36.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "cbb1b701bcb601351ea03bce7c969a8e" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "dc2280c7effa2d9e2d73f943b821d489" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "66856457451a8cf3ba291bea1b222f5b" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "8abd00c58f7fa2f65d86aed9ffb6d183" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.37.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "067bfaa5a0b592b5f5a297cdebfa0182" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.37.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "917019c7eeb2075936623c406df60778" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "405fcc2b800f9ce60ae218b250a0c299" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.38.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "49dfb4fddd08327da242c85ce1d221c5" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.38.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "01a0a6f9c706342a2072200fd6da2ba9" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4e7926d3b598a026b9419dd52fa7845f" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "14bfb7d7779afdcdd63fad8a851719ab" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.38.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "fba377d28870a9369efde114caf00062" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "db6a9c37135f68c7de2aa4deaa0bf3f4" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.39.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "89955b4c47fc33584d76818558ddbf42" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.39.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "615cb450187c74cc2502c071c165a203" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "96216cc913020ac300302e1ee6dbe704" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9947ee7f75b88209029e12a7790c7f4a" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "2c39dcfd6b4dc5d5d1c7769389c94f30" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.40.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "13ff2562989b253b12e086f9549a21da" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.40.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.40.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "77a35fb3518ac216495cd5f6d5ecf53d" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "634c07af399865c8e318a201fec3a2ed" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "6a260b5d5e65d43d0337a1eed01a4fa0" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "31bcf8eb77d08f8af88042d0ec092972" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.41.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "e24685f07673cf5d1dfdb64a6eda0c40" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.41.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.41.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "9885db09f73c68e30125991ad3dd76b6" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "5f22286227d5e273140fdf84ab9aa878" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.42.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "a59cc39621d85f6c12d37ebffeff277c" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.42.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "7b8380d74cb61305158422f312d3ac3a" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c51a6e38a521cb6056b6654a4bbb42e4" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7eea2a264745721687ef4d6b9a61b610" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.42.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "5cd1f673793eb6af8460d24d93c94c31" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "507991384a119380634d8ea2141a5398" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.43.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "e4a9c20969f34d39574feaa53959a06f" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.43.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.43.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "38e17a2d81ec80b1e84bfa6d9ffc56b0" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5c58d4f49cb3fcd2abafa976b13180f3" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "0dd99de3e0a3b4629187803e3c4b7f6b" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "06284ae651d05557e47c3dcbca3dd819" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.44.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c34e59bbe8b087c6eb7cc9d9c5949cbb" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.44.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.44.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "ac78855f8c8b6b36a460346bdbd497a9" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2eebf8382fde0cde7dbac3553fee13c9" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "890e7a1478b7cbeeda0fcb092cf59d17" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "e0b928c237e3291a37eaf31a83dac034" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.45.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ee525050bb9ebcbf70adf25bb32c0758" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.45.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.45.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "ab2c25bb7cda475837de1ce4b4683378" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "89b5d0573c4205496196f6f787aac040" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.46.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "5dc34ad9797102c95399c31621d22ddc" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.46.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "11530655e34ce92d34387a72bff68d7d" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "85fbc10c154e9cc11e82090aa0adfe06" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "fbd836decb929b69a9714cd30568f465" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.46.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "bcf4458eaeb23c5cd4cce920c159d570" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a48eb72b5ee9c6c229560b5ff1d1ac91" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.47.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "528dac58b9ba20b4ebfa4624aae5eb28" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.47.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.47.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "dd0bcfcbb9d430b371716d22dd134cc9" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b1611a9f45109ce8fb8da9dbd7a96f06" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "ab1ca4f8504eee25725de502e7ee44a3" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "1ab02918a52ac3dccd2b8c4f1b903697" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.48.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c420ff7416d511fe617d75e5ac702050" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.48.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.48.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "4c950e01fecb43a4eed4ced896989ff0" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d10c71c90300347161c3c6609643576c" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "61c3d3c5e5d322d0ab10631c3e3cd337" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "4bf60f97b86151a3cfa47911f443ec8f" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.49.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f7ba2d9013b36b097bd1f7e6ccacc645" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.49.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.49.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "55cdc5b1ef444b4dbfd13ce6af78efbf" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9f5eaeb61e4260ef77d151799eddc85b" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.50.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "e9b68bc01cb1f2bd5df6b84341316a72" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.50.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "4f3fcc19e855a019adbaa2000c65c4f5" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ef3f50b584460b8e0dff2a501d75f08e" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b910683811165418d8107e57cac30061" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.50.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "1bb33f1c98108a489d7d5c4a5234b4ab" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4b9505544788fdeba8cd092a351c4045" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.51.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2105e170bb2fe01d4ec0554094e468de" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.51.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.51.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "9b59bc94b6909e254ca1be1ef9e0ce7a" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8f38e50fc964eecf9e7012a3a399f33b" }, { "dataPath": "params_shard_259.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "86f28258d93772ec485fbcdf515c187f" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "98c2010da9b7c157370ffb4bc78ec79c" }, { "dataPath": "params_shard_261.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.52.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "01533542ed6fe702582f1d9cd8d8d695" }, { "dataPath": "params_shard_262.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.52.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.52.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "b45b9c53a12f2a3d3505a0d68aff2542" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "79bd2509a3fe94f2ed25336ef8d9093a" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "1df622b4a3ddc9145d18d292d05875dd" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "bbe39e714c896a82e33f369b33706e16" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.53.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "beed7f1711fb8eab1e9a520721c50496" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.53.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.53.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "68eea2c97fb4f9431690337dcc2d5254" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "9143afc727b523a45ac923af4fd0bbcc" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.54.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "8ee4f6ac0234e88b76c424d395934eab" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.54.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "b04b5967944d2133d212813c3b341fda" }, { "dataPath": "params_shard_271.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8cfecf9a5654ef5408222124a777a2e6" }, { "dataPath": "params_shard_272.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e20a32c5deadcc8b881876246b90ac22" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.54.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "69cdda9d663b1702fe30ec3e9e4bbbdd" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "b057893fc5988c020908029e927df0f6" }, { "dataPath": "params_shard_275.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.55.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c54fd10a6aec77bc2ff73e66c42c78fa" }, { "dataPath": "params_shard_276.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.55.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.55.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "4547e6c108073c618f3113a740346c1d" }, { "dataPath": "params_shard_277.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4b4d61ce45d2a81b0b00ce66efdb2bb1" }, { "dataPath": "params_shard_278.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "bb5229dc5b718b20e416980b1b7d3676" }, { "dataPath": "params_shard_279.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "34fc3b2af5d33804694ffe39c51c68dc" }, { "dataPath": "params_shard_280.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.56.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c558fb5185fa11ffb5b3a2b96b58b6f9" }, { "dataPath": "params_shard_281.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.56.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.56.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "0de2a541d75a07aacb443bebd4a9d761" }, { "dataPath": "params_shard_282.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "15ba5ddf5d530071687b3c568f8fa4ee" }, { "dataPath": "params_shard_283.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "bdf66df3d8076880944e6558ae17695b" }, { "dataPath": "params_shard_284.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "55fe6f6b4d2d639bd47c10c815203ec4" }, { "dataPath": "params_shard_285.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.57.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "05181c2856f654c66553f9a0b797b39e" }, { "dataPath": "params_shard_286.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.57.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.57.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "51dc1c287527ba4b7ba93bc16f782f64" }, { "dataPath": "params_shard_287.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "4f6a9e4c1d3e4820c47eace9b6662da0" }, { "dataPath": "params_shard_288.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.58.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "451a74f1a0fa5d81d613c0afb45fbd2c" }, { "dataPath": "params_shard_289.bin", "format": "raw-shard", "nbytes": 32475136, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.58.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "64d6be4a58e187ee23f11c48dd98d2b2" }, { "dataPath": "params_shard_290.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "099a74e41782ed02013be712ad1d8a04" }, { "dataPath": "params_shard_291.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f97d21b56dd853c2360a86a268ae2770" }, { "dataPath": "params_shard_292.bin", "format": "raw-shard", "nbytes": 25896960, "records": [ { "name": "model.layers.58.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "b0e497c942b0090cbe2e5345d3f0c149" }, { "dataPath": "params_shard_293.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "a37570f4e0c0412fa1151cf3463f7a5d" }, { "dataPath": "params_shard_294.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.59.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7e338df233773c1db38dc08dd12c3247" }, { "dataPath": "params_shard_295.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.59.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.59.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "03e9aba8b53cdc304051df13c41be4cd" }, { "dataPath": "params_shard_296.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "9619580854822a4f2e93e22b47d0d58b" }, { "dataPath": "params_shard_297.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "bf5eff06484330ef72fa7ec2b6a274f1" }, { "dataPath": "params_shard_298.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "aa4dcca1066046b060d4b495bd89df7f" }, { "dataPath": "params_shard_299.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.60.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c7e1e2d0cf7a09e9e5a686d98d76a11b" }, { "dataPath": "params_shard_300.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.60.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.60.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "b453a86241b892f314ca9cfe38f14203" }, { "dataPath": "params_shard_301.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 5120, 3456 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "79846e9cd844830d300d98f6fd5ce4b7" }, { "dataPath": "params_shard_302.bin", "format": "raw-shard", "nbytes": 141557760, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 55296, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 141557760, "byteOffset": 0 } ], "md5sum": "14a9f5ee3c267082a5679f117c256995" }, { "dataPath": "params_shard_303.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "67f593da30e6d297143ad0948d8fbc0d" }, { "dataPath": "params_shard_304.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.61.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f6595d4e16fa04e5d59eb510e1df21d9" }, { "dataPath": "params_shard_305.bin", "format": "raw-shard", "nbytes": 25921536, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.61.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.61.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "a5bbf2d1be86eee67d6723f14a185bff" }, { "dataPath": "params_shard_306.bin", "format": "raw-shard", "nbytes": 33130496, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 14755840 }, { "name": "model.layers.62.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14336, "byteOffset": 14766080 }, { "name": "model.layers.62.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 14780416 } ], "md5sum": "de5053ec4fa843d51ddd984b5e19925d" }, { "dataPath": "params_shard_307.bin", "format": "raw-shard", "nbytes": 17039360, "records": [ { "name": "model.layers.62.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1638400, "byteOffset": 15400960 } ], "md5sum": "ae19e143d242e1e05cadcf621def2750" } ] }