{ "metadata": { "ParamSize": 709, "ParamBytes": 18431289344.0, "BitsPerParam": 3.4681150523128728 }, "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": "451c91b2f61aca9372e66c52ff7466f2" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 48660480, "records": [ { "name": "lm_head.q_scale", "shape": [ 152064, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 48660480, "byteOffset": 0 } ], "md5sum": "1baa292d0414355a745ba123a40cb510" }, { "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": "ca9e7a6a1be6a4699298fb22443281e2" }, { "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": "ab79014c50d3bd4162b9d88ce185b86f" }, { "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": "7845cc11daec41897a515ba3e3b43f94" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 26552320, "records": [ { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 } ], "md5sum": "3cdc49f18934969386a324c81e333126" }, { "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": "85b78af4b742f05d4209e914d977c80d" }, { "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": "9c68e8fa2e3517c8e9b07b3a8c6903cf" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.63.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.63.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "8149fe05c254e79d8e923454c81e84ac" }, { "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": "93ab4691faebb2e454269e08f10f50c7" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 48660480, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 48660480, "byteOffset": 0 } ], "md5sum": "8e363470707b24dc69e802f4cdc68d17" }, { "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": "cd1bf810182458d6614c2c2a1095dba6" }, { "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": "629c93201b1420ad1fac98874839c49e" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "5d8f87060b7978fc8cf47e875329641b" }, { "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": "40c3bf50c1c7dd1e34f9da25237b8e9a" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14755840 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14766080 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23613440 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23623680 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23638016 } ], "md5sum": "14b0073f1044bfd7f970c4d98b005eff" }, { "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": "5e1d650b6710d04395a7adb596dd2f0c" }, { "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": "6c20c0a5fb54a162b2106ce5e1533ec5" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "ce3e995a60d255c77f7c77feeee9984a" }, { "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": "d6312a247fc0547108c24dcf91ea7afc" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "190c520025e447b76ca6e93fbbfc2056" }, { "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": "db3ffcd8f664735261afa51e85f1bbc5" }, { "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": "546f5fec37f3cf09e3c3ad61e06cb2b5" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "bbbc5ad5d0a33f2dc330f46a32e5896b" }, { "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": "050058d1dc8286e7d666aa56d7d1dcf7" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "599fc41cceda31701bc925ddfd85cfd6" }, { "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": "0ef10128f7b47b8d2a509a6b218932c1" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039360 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17049600 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 17059840 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "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": "11e38540da83e1e6d10bf49734c2bc6d" }, { "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": "4e87abcd560e6e022d8f5c6401cc6b80" }, { "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": "c62336ff37955af0cd3df44d4df56a0c" }, { "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": "0176429c2b3ed52cf5625c3a3daac3b3" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 0 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 1638400 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 10485760 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28180480 } ], "md5sum": "b5762f2471b18d9b3442c1532a17001e" }, { "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": "dfbc03b740d5ab3ad360ae1018edc14d" }, { "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": "37528c2a5b332bc155cfa84e62730352" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "20e66b2230d06e4cfcd64843867f0ae4" }, { "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": "b4adb4cb8715f7a26e6bf3ee39ca1c55" }, { "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": "a697fcc3a3ee79e67ff09e64f5fd91f6" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "f51ce0e17935f87a1add75f35ba3714f" }, { "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": "9c74c2e72ef999dca6c090b7c8cb527f" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "a397167df871dad52b45a09ccbc6faf7" }, { "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": "0c75adf573b289c5c6b09241620ef228" }, { "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": "ec0a46ffab6511883d21ea91a6d47468" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "a1ea5a6e9af60b7df0b9ce58eb4dd1d1" }, { "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": "e691c0a679fcca84ed06231655440a97" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "a77ea04723655db7c11c55abb9b34577" }, { "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": "6f0b6cdb26cb71093dcdf79f153a4e62" }, { "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": "2a7411f9e63e230a921a3c1f181fac04" }, { "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": "1ac3a8f3b606298d351a578bce0deda3" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "3d39ba34d8129e9e4e5c2542f372790e" }, { "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": "229589b889b8f50cef2dbf64f6e2bb32" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23592960 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 23603200 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "101115ae977b936d4398986ec3ea54c7" }, { "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": "7f23e6126218fca7f2bb861090d638d3" }, { "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": "9bd7e0ddab7ad48c743d2fea3361a295" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "fb4742aebb9cd3c6e155ff02587cc4c0" }, { "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": "67aa4a62afbf380e1e6315cbc915236a" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039360 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17049600 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25896960 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 25907200 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 25921536 } ], "md5sum": "5be347d648eff70a9859dfba4ea468a6" }, { "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": "6f97c3f3fd95a831f73eff2a0469f3c7" }, { "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": "78cde15ef972157b43b5a0f47c17e5ae" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "30981913accbdf02f49a87e899d13338" }, { "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": "5cefcd8d87f86f6228bad97f7643f0fb" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "aed182a48db2342afbf532601c2bbf94" }, { "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": "4c42101c9fee7db9445c34f02ccb848b" }, { "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": "e0664bbf727fad5a75dc79aefd6e3092" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "3d869f02c7aec7c0812895c0edc6bc2e" }, { "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": "cd41b2dca5b6181944fedfcd038ed72b" }, { "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": "45890925dba392eacdaf84d91088fe67" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "6b36922ac1eeb879f93ad45df997d87d" }, { "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": "ecd9e8823b998a7fba8ce6b4aa5d46cd" }, { "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": "c4947c0fd5578395fa71f5b4d66e6843" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "9c85552e54d35cb3905b775a93ea101e" }, { "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": "e983c1567d480ca941588cf72a56a28d" }, { "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": "a9daa32cf2492d8abbb48bc862122704" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "c1224db881ca45c5b08a65ed5914abcd" }, { "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": "9d80f8cf20a9b7631874a6456851290d" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "cb839662a0d63b29049584bb49c1d8dc" }, { "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": "09d2da4b6915e306ff765bcf97f4d867" }, { "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": "886044254cde6d462d642a8ba046ad8d" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "2283f0a581bce5fecb15c9891660ff0d" }, { "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": "88b1991136b2998a54e29602d0fb4103" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "5e924ec750a7cfa8d62750497a2ff2ca" }, { "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": "c17927a4a6b62ffc848b4aed354cc97b" }, { "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": "c23045cfc5620075ebde61d559cfb907" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "cd320557f287df47d3b34b2532cc7867" }, { "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": "068873fd99528ec5b47cae7a0ded980b" }, { "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": "b733c5c9fc5087a82d720c179304cf2b" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "6310a42d021bd2ba961637b9e4950c76" }, { "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": "8d01eea80b7f553825906801a8d51e84" }, { "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": "4d422e27164ff6416cdb00ca157f026b" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "80d28e96b014bc0c4ab7a641868f6865" }, { "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": "5323f66bbff5925c55e0c1795ef222c5" }, { "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": "20785555650f6c716c04a63220d08d87" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "9a39eee80104a7b2c3120f6a3211e70f" }, { "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": "d91a3c9546f7b149ac9b933119d2cdcd" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "3b8ded95122c4c176eae506cc5f6a2b8" }, { "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": "8299597b01980e6850b5a402bfe0dafa" }, { "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": "d3b4db7dfc0fe8765968b97f48e9b77f" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "7f1b804d4f67d63c75af70ced320578b" }, { "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": "f5fe43fd4c7bf3fff0578ef005535de5" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "85e0a3467eb02a703ed1b2027758c2ab" }, { "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": "f21903cc3dada0f3d090632481aab126" }, { "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": "81e136851809c9ff596b0eadb0eb4be7" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "acb9e0b41750485efe4a460668aae3a4" }, { "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": "28c17e0d343d285c28cb42a875d7e1f2" }, { "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": "43072f39552f115fe466265a99db5d64" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "fd6a127bb734431acd03863c12a061ca" }, { "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": "2c47200fd23221fbe848789b8d07dee3" }, { "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": "d1117c21ab7dbb2a0a632cdfd1f4e3a4" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "d3c555940863870e109d07d288216071" }, { "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": "65d48ead4cc8591d5bb60d920c38ff13" }, { "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": "0db2fa874a28d1ab8dc8871c99ea3abc" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "0552c1f020b51033bc9eafe6461492b9" }, { "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": "a6881e84d7d08e8b1d656c36dc465264" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "feb56796f0188ed9014ce1911197fc75" }, { "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": "62d931d8365a3e682ad024a31c4b9f0d" }, { "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": "93d0194b0c972c0afef5f8141558e817" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "610c933cbc3b00b0162c40dc7453f56a" }, { "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": "b719cfc981bd705101a1ec210ef25a62" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "73a7a4fcf1b2fcfffa6dba484a74871e" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14755840 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "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": "a8f79b168e7be2cd8667231ab753729d" }, { "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": "830f7b63e400f4db603b686beaad4ca8" }, { "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": "1f6c522a44b64ff8b647566a3b5e1e86" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "482878010eac3d1ffb825cb6943ca7d3" }, { "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": "180615027752dabef23383c042739e0d" }, { "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": "041e73d41fa979e703e93c432fad106a" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "b07572db47e157a43f33bd5d80be94f2" }, { "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": "24316cb36213ae447253ce5a640ac677" }, { "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": "9168fa474efc8b5f44d15e7c7c308176" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "4e299307878a36d7719f0ae83f79423d" }, { "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": "3062734cf73d2f12497317bc33dff79e" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "c1b6a856f81672dd5627f856c772e1ed" }, { "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": "f6071541972ba5abe883360d02bceae5" }, { "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": "fe6fa5895b9bb30c824153d24daed25a" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "1586db129fd0d7df244df1c2582fe340" }, { "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": "738bae26402349ed027d574496aae78a" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "674b210920ef347af38002c51e4bae5e" }, { "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": "a28c27af6ab8441a02bed6a2ff87b46d" }, { "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": "e65d5247388c7c5481dfa7e9dc4fa9d9" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "256627b8e3f6565b15298e8cdaf4767e" }, { "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": "0a46f4c798b96e4c6e5176118607e31e" }, { "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": "39b1026d7481383b879797b7c6aed49a" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "9fc5c5fb12675982bd2f4e208321e102" }, { "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": "42b712a9051eb5745c9bafdf673e20cb" }, { "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": "649c22d6f1445a02c67c7db3d5430c3d" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "d5e0d1929597d65d8af8f6b9dd139b9f" }, { "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": "f3d3a0763aa24ab3774ed7ebaab02a62" }, { "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": "696bf9c52f0be3999a2f6ea22c5c4f56" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "ae963d98a729bfd070ab07a82a345812" }, { "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": "c121316baa7b708c67601866545ef084" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.28.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "1f65c0d5a8e88ae1c748916c4e1b5d38" }, { "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": "d0c3076756a22fc4c26c48906712c367" }, { "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": "97fa13614b41f292d5224a40f2a73f3a" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "818dbef71166b549c10106e7f79a87a6" }, { "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": "46457abaacb7f6aee9fadc8e73dfef98" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.29.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "e7c1943422625da63b1c926ef0358515" }, { "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": "d8b2fff77924872d16b8eff8eb6a59fc" }, { "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": "a1884c8ee0a54ccd7b584bb0b0a6aab6" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.30.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "0f791ed381631274276a10b8dc05ab29" }, { "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": "67a032ace0c0c3f40e01b12415c6d3af" }, { "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": "989d873c6a030732dc01af95dca4c154" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "6ffc61d019503ae6194d22195209ae4e" }, { "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": "716898a6dcc256fcbcb15a8e65fc04b7" }, { "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": "e197fa318675feb88262b4dcbb58a58d" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.31.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "a21bb94dc8876b12393a40a9cd83ad6a" }, { "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": "908987d9fbd523e7ee8aaa7b931aa2b3" }, { "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": "c0baf39ba9a6fb1638346d1196f6a949" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "197ee2b017be7b70c53514ec6c48248b" }, { "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": "76f9651ed1699d2a46177514cbd76862" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.32.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "00ccabf3dac022e6363a16d1ab0c7c57" }, { "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": "4ecd81022be6b1dc08c8af1cacb88f6a" }, { "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": "8d286c14c2eb8c2dc3911c444a88f37b" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "7efb3541a394fc510d578083d0396b85" }, { "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": "6bf7be7d1a998bc42e4e9cdd0c816f38" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.33.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "698fadaede109f4441e8ead8cdf2e796" }, { "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": "f42e5864c1140f385a565bd188252f11" }, { "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": "beab6932f1e668cb01b26d1bb6c1e1a3" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.34.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "db212ce5bfc756c1c7cb0ab4606b8b69" }, { "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": "1e3e810b5d9d3f4903ae2c36504de75c" }, { "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": "2a94cb404d32c718cb16b503e2111c3e" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "a7baf820cda29e6ccc79e3c57d29502a" }, { "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": "058066c0a3fcca23d651e62bdaa6a837" }, { "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": "e5f50773019c233e4761959b10b5e175" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.35.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "6a8cc33955334b233c84d4b35c9a7e02" }, { "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": "e750784a2979196fd6413866e6a7f579" }, { "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": "a965b8e24676869a1917ea5fd0ab07ca" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "bcd8ef7fe1fc777c4819b1ba0e8ad6e3" }, { "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": "1ae2bd68a87dec8cf38be96d603126fa" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.36.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "5cdeff6ff3fd0fc348c114356c427ad4" }, { "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": "805ac66e9b697f3cdc15239a20acdd48" }, { "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": "d24518d53f99acbf4f664c2c77f190d9" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "3f05d9ec1c25f4b60e8dea731ab4559f" }, { "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": "520de23d708bec1d6f29502830320b6c" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.37.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "532db01022972d3f89b3ab4e27fa1731" }, { "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": "92a208456155ef9d1f3a61c31a0c85b2" }, { "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": "1c1bf111d52b0555b353501281772d0e" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.38.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "0dad915336294f6d9053065b37e510f1" }, { "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": "380500e93ec00cef66025624b8c7c297" }, { "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": "00425a0a8cb097828f6ee6d3d3589ffb" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "020a1ee02fd1520330bdc1ea29c56512" }, { "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": "0073751250dd1ddf67d24bea795a9f2c" }, { "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": "b08d3e047c1485247afd45ff455f1230" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.39.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "a760aa328c1939c77dc50c6a8a1ca94c" }, { "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": "0ff0c909b6a646f0ea56b6b0bf8561da" }, { "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": "ef5a3f43d331e953c99a204a97c0e6af" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "e13d64600399992ba4ce64387be4dfaa" }, { "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": "8a142d0ddcc77068ddf19e4c7c6dcb51" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.40.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.40.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "5161f16952982d9862d38f0dfd97c8d7" }, { "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": "15aa0a7fceef23d17ac9f3c5525314f9" }, { "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": "68794ea49bc9dcd789af38ee00f901ad" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "d8e2ae1fdd3c713baa60a25f54dba987" }, { "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": "6e8dd11f4b002116110540f3473bacb6" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.41.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.41.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "d72ace8c15331a5e80ad27d307071da6" }, { "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": "b2e89fbfa26a7281ac4f800aca2b1300" }, { "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": "ef17c59713b545548cf042f9a4328fd6" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.42.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "2416c53c8d999b83725295b2344e9623" }, { "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": "e79821928934728bc0fdcbea39b59ffc" }, { "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": "321b02c46242a15dcfd5c2e9c0db0cdf" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "0b3da51569b0ebfe631b3e069d973301" }, { "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": "03c1708a004a30626ad52764a9b3e5ce" }, { "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": "867e8963e1f2b437dbaa423d0069acc3" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.43.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.43.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "dcd2a49c1cc4b25f5b999c1f3b5c748a" }, { "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": "82016d57219c7fc69abe6c3ce6868d2f" }, { "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": "0a850318b3f9264042f51e0acb4268c5" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "721713d1d445cb11b7db00079df98020" }, { "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": "d92b60a197ec2f8d6e52d3ad5193c444" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.44.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.44.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "53fbceccc7ed47e4349fb1c6ca7d4d25" }, { "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": "6841fa5228470375500e19a5d7cc4908" }, { "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": "1230413fd7150611394a97718fefb51a" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "bfb9e7fa49b1d410660636411fb3972d" }, { "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": "fb3c6e468463cf44046ba96974dd716e" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.45.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.45.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "3082d9ac0db1155aba052cbd4b435834" }, { "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": "ae879a16e605b7bc4b19834d0ea7c6e1" }, { "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": "850bbc9fdcbe62cbe718e05e6b2ce716" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.46.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "1ebdbdd5b70c5575325b0d5a62b67443" }, { "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": "cb13c8d0e748d80f3d314aa44ca0e5c3" }, { "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": "750e9d6fa4b67ae2a2091e2d2d13cda4" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "3da0111d00c71565bfb3a591d74bc43f" }, { "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": "fab697f6204f3332d8db14e6231e92a9" }, { "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": "3fc5c62ed38b4dc1045da52d772a8f0c" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.47.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.47.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "be2bb0ad80e0cbfd38559e56f259fc00" }, { "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": "50ec3b817989466583959ea61422df06" }, { "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": "893a914c2f88d8ed7c369d0410557865" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "aa1fe1882fbf097f83e9843d4304bb83" }, { "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": "37726ddcf4ab3341a39735366decc7c9" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.48.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.48.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "8a067556a2af8728a463fce2646a1203" }, { "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": "16b4cb8e6dff5e44c10d3a7ebba77878" }, { "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": "01266f113d08d4e2f87a855d4acab082" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "b83458e47f2d8d6fae80afc537ecf4e1" }, { "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": "a5d5c6ef322a48e8d614b6ce9ff44c21" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.49.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.49.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "af97cabee48040dfdc428f3d0a1ecac2" }, { "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": "725e0b67be6d1b97531cbf52b606db20" }, { "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": "d0b63798cd1b4eacc2c6e6d42c550e27" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.50.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "28eea7cad12629385a9d4d24d640366e" }, { "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": "5aa872bbbb290aab7b0e66fc968aa8e4" }, { "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": "ee159eaaf5858846f05134d47ad8c02d" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "f1f62cfbfc69ed1d4c587c6318187f08" }, { "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": "23bc759adddde199f65c04895ee2ef30" }, { "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": "df3774dbba39165a75e89e4ad6a59ada" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.51.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.51.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "1a07f57c8503a11cb558cb836ce0eb5e" }, { "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": "ddb764c47aeb214c22df69c7009cf9a4" }, { "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": "cc293b240a3b6688dcd19995b587fa85" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "db4be732f06ff7ffd291ee6fa0b9a782" }, { "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": "22e28f5571fdd9a1320b8ec155077f39" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.52.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.52.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "7aa6178a41b8e4ce3c5880e344245979" }, { "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": "9509bca30048851b9c1fcb7fbec51bc1" }, { "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": "09ce9a8547ba8e9c529b2f5c7c308473" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "f048e732531f9ac9246f581c15fa44b1" }, { "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": "c837b2c1d9b0b44991df906243c5b13c" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.53.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.53.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "1d5b93aeebf8de376ff1df0cd75674c4" }, { "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": "4f789377ed7510fd540e13e7a892f2e7" }, { "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": "30b2a126baac489b18a2c31ca3606bbb" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.54.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "3b14add75ac8f64a898cf27392fb24e6" }, { "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": "74d6a0873dd134306edc3099681e1a3d" }, { "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": "485c45eab767187c41547b9e883b9817" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "5a75529a1d3d5379a4610f3a613b4aed" }, { "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": "ccc0edaad4b52f8b68abb81a8f935e08" }, { "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": "0906f7e78cb0f19d0839b9a14cff3dc6" }, { "dataPath": "params_shard_276.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.55.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.55.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "a7eedd9385bd05da45ac7bd781ce43e4" }, { "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": "7b475d2264fbc541b44607ce1fc5314a" }, { "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": "75fc6959486bcf48274f7b330df0177e" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "1d2be81470f93eb153daf7d23a0d291b" }, { "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": "2761637efc0067cf555f6e1f73a6a174" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.56.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.56.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "e2d2e6c52baaf988861510d99ab376ca" }, { "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": "b50f626fb2bda4eb9429a935b346345a" }, { "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": "90d0dfcdd5a6e7956d2d79e88e96084d" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "f51960f3f0e52e5df6532cd526eb7ed5" }, { "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": "33177bc9febdd88f6b5bbc8661aa91ea" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.57.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.57.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "7ab374d07517f2b440676d684f420f2a" }, { "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": "7354451b49f03f0974ebf2b3ac03a2c5" }, { "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": "0859bf851897452cd17fc6423e21dbb1" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 14755840 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32450560 }, { "name": "model.layers.58.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 32460800 } ], "md5sum": "6982ccea7c9b695c5e5d9b78194f581e" }, { "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": "960f9fc04dc9d3ef56ead36286af959b" }, { "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": "f8d440477a1c06af12726f7193f58e91" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17039360 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25886720 } ], "md5sum": "48c2ad0977691e1b403ce72ceca216f4" }, { "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": "f6ffdbbbe539896b549b42dc0e57a1b6" }, { "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": "e6fee88ab6f7d99810ed2d6ac5d4769c" }, { "dataPath": "params_shard_295.bin", "format": "raw-shard", "nbytes": 28860416, "records": [ { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 55296, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 8847360 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26542080 }, { "name": "model.layers.59.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26552320 }, { "name": "model.layers.59.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26566656 } ], "md5sum": "d79433af0d8522141b5a47f44f41e331" }, { "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": "05cb388c6fdabe76fb6caeabb8f809d9" }, { "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": "4e7d968997f85e9156a7c6e6d2718e09" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "83d510753382c2457aafe0c5dae7883c" }, { "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": "a20b30dfe7c7fba6b8a91843e556812d" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.60.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.60.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "96e7fefb607e1543c6926b236cbbd033" }, { "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": "401336354d8e9da78a538449ff53b9f1" }, { "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": "6d1e0f3c6de7dc49629b2e941e04b052" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "1cd9fd7c3004ff97ea4a91e29e88cff5" }, { "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": "a0ee099f15f5c9f649ebd29ca38620fb" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 5120, 864 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14755840 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 23603200 }, { "name": "model.layers.61.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 23613440 }, { "name": "model.layers.61.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 23627776 } ], "md5sum": "46767e0f35d251858b08ba03a1dbcb7f" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14755840 }, { "name": "model.layers.62.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "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": "37b783cad324ba462255f45c063c3961" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 } ], "md5sum": "d793a30e33157b321a9d32eb5e3b99cc" } ] }