{ "metadata": { "ParamSize": 533, "ParamBytes": 8309352448.0, "BitsPerParam": 4.50065457508222 }, "records": [ { "dataPath": "params_shard_0.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": "4e2b7c2f554abb8cf646a605202a1714" }, { "dataPath": "params_shard_1.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": "7586162a69412b433700a576d8435d95" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 20658176, "records": [ { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 14336 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 18364416 } ], "md5sum": "be8688ef95506ffb308f319d93643189" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ce4d289cbdfedd8abf3c0c04cdd9232f" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "e2458df4ddb4632fe9096a0db8947ecc" }, { "dataPath": "params_shard_5.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": "6feb95bcec40e4fb57160f3b933da893" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 30345216, "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.0.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "c579aafc842695c0d987fce104769b64" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "cf23d4d16e29e82a0b9ca06f3a89bb5e" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "9c7d659304b8d86382c605bd53014cf4" }, { "dataPath": "params_shard_9.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": "dd801accb2ecf9ce8deda53853c41b0d" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 30345216, "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.1.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "55dcdaf4654c9615a66ad6efeadab18f" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "050b667704ed36725dc1401dcc344a6e" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "248dc91e58b6afa613781b75ac15b473" }, { "dataPath": "params_shard_13.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": "8190ed981626ddc1b0ecc9f7254c2cce" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "9e4efa31be7059ff84c3d7b6ce7789a7" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7dd136a7f9a270475229b5626a0704db" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "c88282a65a8ddc502888965ef5c4da54" }, { "dataPath": "params_shard_17.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": "e8c8c9fa31fb66aaf6e3d7959101944b" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 30345216, "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.3.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "252276f88c12965e104e56197ec59585" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5c40afdc37cc819f66b44105f98649e9" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "a90f0c3f5fce9e9cf1231923f53f3899" }, { "dataPath": "params_shard_21.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": "2d0ebc741868bd20aa6b4c40ef35d145" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 30345216, "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.4.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "6e05bf7a82fe6bed2080d6530d14617a" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "299ee2707ddb6dcc3a62bbd4828dd08a" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "e534303d17c9ab1621eb66d1ccef5393" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "9df11eb0c3fb6aa67ead5e2bf6a09a8a" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 30345216, "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.5.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "6b5dbe722a8427522d3f761cdcf75296" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "aff086f9a419e4d6c9b9695f8c9eb008" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "e7a90566239cdec9c33c8461cdec3bbd" }, { "dataPath": "params_shard_29.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": "c1aa110c619a46fe3fcce512181a9f93" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "dc933b7071d5391f9a0d09ab0c46bf72" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "43270bd517332a3a5704967f2f8dfb6f" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "a2b2a2a11681e5e944ef535f1de2e4e5" }, { "dataPath": "params_shard_33.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": "29838f1b46f2ed0abc5a815ff47a4089" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 30345216, "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.7.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "fee3a8198ab978439082e83cfd29e9f9" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "da4c07f441603aaa29b8a929a010b77e" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "d142f5abbd5112306c8d2bf041e988b4" }, { "dataPath": "params_shard_37.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": "7884e7f59db8826b7a15bbdce4cadf2e" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 30345216, "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.8.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "128a5a57bb58abcebe81602520f07c83" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5402978a7de2c2ea36989ac1f0d6eb21" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "dc2ae54c1083c9407d667a10bb5e7c34" }, { "dataPath": "params_shard_41.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": "0baee310a05a5ad94b2c30f6fc25ac6b" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 30345216, "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.9.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "e83353626399d3692ae643c5ab14d117" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "dc391f10e930da3b425fb9464dcb2cde" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "0057bdc54eda8a5b6e27459af3828511" }, { "dataPath": "params_shard_45.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": "d2ef8e868f9f55e256052c8e62c48372" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "852e3790b8a0779af8ee9699da2a5c42" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ff60269b8e871b7263c44a5f4e8aff9e" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "65a335beb8f0e39932d2d9538c5dc806" }, { "dataPath": "params_shard_49.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": "eeffec50f8582a5df4a0c33e9783f5aa" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "1583173afeb74248a3f42c8f39006fd4" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f65814f2499c64b8b54ef4fcac3cb5bb" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "7c1556ea992bf8d0d39813273aa64722" }, { "dataPath": "params_shard_53.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": "8c6dc3efe373038e1ec2cad4ecd020ed" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 30345216, "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.12.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "231989ca4456a3045e96caa718f36266" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "1a0b7da0e472a3f0160d2b13ab2bcd61" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "72d35edeb94214eef37cf1db1c30bcb1" }, { "dataPath": "params_shard_57.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": "0a515f319c03c20c0c0cd4d642e65f4c" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 30345216, "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.13.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "61e6019a6be386eba57d0c2c92d7e2ae" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "9ac2bc5cb2f324c767d9cf137d308e69" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "d1695c64b113e519f2c6e021860d34c4" }, { "dataPath": "params_shard_61.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": "9222c276a265b4430213f9a33b330442" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "f3ed595c9eac0309fcf1113aa8b6b4bc" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "afbf45be6c142153e4d8d61d8c623f17" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "091c03d8f61edcc577f0cfcfd2accb18" }, { "dataPath": "params_shard_65.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": "01b48109ac8d1f08abfa520fd64db3ac" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 30345216, "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.15.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "b69fc4b61dc9ad7a10bff3ee6d7fb851" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "368108862bda172bbbba0e952e74793a" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "8b10bf20e2bb887dc9842af3d66605aa" }, { "dataPath": "params_shard_69.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": "0dd375f196bff56c09c9ec7723c60995" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 30345216, "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.16.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "88e8258140ba628d5fb45e3147ea8f4e" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "9925deb1157a14708ece28f37034de7e" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "6e5ed4983bbc0ae66a559a1e8aafbc46" }, { "dataPath": "params_shard_73.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": "8fb4de013f31495777be69ccc7fcffad" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 30345216, "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.17.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "48ad02d63659410eba00115d59b5b02c" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ed063cca5ffe9e3fec872df2413b8048" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "4a600b7fadf8ce31f8ab7c4d8d07b957" }, { "dataPath": "params_shard_77.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": "fe079bf87d003fcaffb062e4eadd7512" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "d2cf4e51368c3922cd747e65860f58d1" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "51393022b28fb627f6cec02e4d70a243" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "e75d9b1529bd5f90d5450fa2733a8b39" }, { "dataPath": "params_shard_81.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": "07018ccbedd8f48b7d62d2ca0787b81e" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 30345216, "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.19.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "33a3a5b7aa06b4d19d6e3026a5efbfd5" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6554f625108b33b08e24ed9e66acb476" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "5f5b8b7b5f16902cba6ce50f6191f92d" }, { "dataPath": "params_shard_85.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": "c3133b156efdc5a12d645bd9d07e7de7" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 30345216, "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.20.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "1241a8715b868499ebedfc3c73af74da" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b3e003d52b6a089a189e9cf09780662e" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "b8c732b8816b0f00b0201dab1762bdbe" }, { "dataPath": "params_shard_89.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": "f3ca6a3475ce2904e20c98cdfbe6070a" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 30345216, "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.21.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "51e0146d5a5ba21d22cc47aa8b1c63d0" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4c3f5a103bb5cdcc17615c27d6528efe" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "225a2622a15b6c5129d77613ae9b62a1" }, { "dataPath": "params_shard_93.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": "66c5ba1f01363cb983fd193790d1d0ed" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "8aa28ec39839475608115af006be85bb" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e86f3e968003b5a8522e6bbaa96aeb4f" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "4909c895361f329634dfee06abd356fe" }, { "dataPath": "params_shard_97.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": "fdcd857b20ebc403b341ac6b1d37cc35" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 30345216, "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.23.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "760d22eb917572a92b8246387a8b1886" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "fd128b62c82bca8b465832c945e8eebd" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "0284380347fac22d38ea969cb21b7d14" }, { "dataPath": "params_shard_101.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": "fab80a3209be3ff5fca46e32bd7229b0" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 30345216, "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.24.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "46bc16e7266aae13a81a55f6fc06cc5e" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d2ab953087b85444654dcff6c4c0afdd" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "cc014b16b28146553fddac42a7eee2d0" }, { "dataPath": "params_shard_105.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": "063b28f0fd9dfb4a0bf6f0e16d047802" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 30345216, "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.25.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "36ce81499e91f9e4494e24e8b009dbad" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "eba180bb1ce51bdad1eb2a65b39bc113" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "66c04913962dec8bd78582590ae3f933" }, { "dataPath": "params_shard_109.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": "9a96ade1a833bf132e4aac544f42e71a" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "10168738fef484b1393b51cc62075632" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "0817c8ddcf67d07af0b9b998f58649c4" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "3bdc574771b9973cefc29c160c99ff0c" }, { "dataPath": "params_shard_113.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": "33d30898beabdb84c5ea9cebba0c78bb" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 30345216, "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.27.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.28.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "343cdcc577c4f2eb7134bfb819183bf1" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "611aaa1a6ea804efe022ec35d2bf5450" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "f6b0b9d1d58bb09711ed44e5eda2f25a" }, { "dataPath": "params_shard_117.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": "f6724063d59eecb826eb009cede88e53" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 30345216, "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.28.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.29.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "7749ae20a95d43e3e878e00b07c56460" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d2aa93b7c48955d6d9a2b9645937b6fa" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "254e9227c00d5fd8b76f8b051cd7cff5" }, { "dataPath": "params_shard_121.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": "66c27f97ba857fa51c186d74749e4acd" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 30345216, "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.29.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.30.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "401664e130f4cdfeeb01fd8a7eaca9e1" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2e2b092aa2554eb99579610747beffc5" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "3ec09f0a727966ca1654d4152a31221b" }, { "dataPath": "params_shard_125.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": "c1a8bb3294178977c5474745837f6216" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.31.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "e11ae7667dd07ee1f4f623a004258ade" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f1deac07d5ba935b47f5f6da1d4f70a0" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "be890b006fc2b2df76a81ffde1dc52c7" }, { "dataPath": "params_shard_129.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": "5f347d218d00643d37d1afd06288354d" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 30345216, "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.31.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.32.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "1b2d6318d43e90ac2d7d4cbde8552aea" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a6c0475880f159441d3cec27447c3c2d" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "22e131c97bb90bf4aab8575e913962e1" }, { "dataPath": "params_shard_133.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": "277fc3ab72bee2a904821f91bdf6ffca" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 30345216, "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.32.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.33.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "4ea7a9681da3bd17af661b118593708f" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6f4a7bcc0f6a4c3396f3a72e338c5beb" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "eb724765ca620f479e7d41532dd79eee" }, { "dataPath": "params_shard_137.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": "f98b7b6f9a8191c3e6a0c861828f0851" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 30345216, "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.33.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.34.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "d0755dbcacb673eaad924d0f73046504" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ae039e6a2ac7037d8b659a455527e163" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "356efe0397085489b5812a92d0b210e6" }, { "dataPath": "params_shard_141.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": "2d040a4faa83e0bd11ee98ddfd47cdab" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.35.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "c2348afe9df31bd323746839c85d1302" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2d21b5becf31067daa451387afe64772" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "4d387ee1899a01ae4cd38f135036f376" }, { "dataPath": "params_shard_145.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": "3210aec4be7814a8e91fa6a9a3ae96cd" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 30345216, "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.35.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.36.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "64afc9b7f7bb7406277ed8ce6b30ae60" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "27a75f0f0a3f0f4bb07f44c12f1b7b72" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "6435563726467b5d6643facf860b5751" }, { "dataPath": "params_shard_149.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": "65ad67c6f2687c9b5db2ab00256aa096" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 30345216, "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.36.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.37.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "b36a575b8077dcf54cf58169f6a05def" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "12005a4ee322d6303abe953410a31c1a" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "91c2c35fb6f942a65038232e191a84bb" }, { "dataPath": "params_shard_153.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": "2d11a53d5ee9cb908df1ce376ee2e0cd" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 30345216, "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.37.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.38.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.38.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "2e842367084d211561101324906ea4ba" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d7abad7ae7a95a96fe613eb64e3b4cb1" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "9ea7aeda9a1c425e2c330e0202612d57" }, { "dataPath": "params_shard_157.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": "99315bf16b250b1c9c8c95fe65873434" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.39.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "ec1a2b33e0a8c272af171f21602995f4" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2c01388dae6de2e91e2205ef7da92f26" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "ec6eca12e43586c6a16773c3158f1853" }, { "dataPath": "params_shard_161.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": "96350046b567efdd46784c7295d67521" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 30345216, "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.39.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.40.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.40.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "d62d4fc95133b48c0585dfd889dd4a99" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "9c4f540e4af1a8e8c65af03aad8d49d0" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "6885ecfa06b9b6313625cc11fd7e854a" }, { "dataPath": "params_shard_165.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": "498145df38e6ee127c2e875f991b3408" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 30345216, "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.40.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.41.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.41.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "c3596cd0c4638b412c9be564a8bbb063" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f2bd9959ede8b1d82523d7ed35f270ff" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "a7548acd61692bec44f16b3906580b20" }, { "dataPath": "params_shard_169.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": "412c6b8f0b15a549a102ff4a151d45fe" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 30345216, "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.41.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.42.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.42.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "395bec707c2651e765e184d72433d7fa" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d7199a6274dff9d5ce714656116d8167" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "95bd80d603d77d95d14374d6bdf6004b" }, { "dataPath": "params_shard_173.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": "0228326802c696ce041872d67d4521f0" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.43.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.43.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "5f8613b8309d06e710a9e01bad359720" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "dac09fda136caa48c57013e1509c176f" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "b29611e96688f14cbf3c490433ae419e" }, { "dataPath": "params_shard_177.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": "2c60a37ab7b784b3a1903580a869b6c0" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 30345216, "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.43.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.44.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.44.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "9bff0eb52639e5ff165bfafd116bf5cc" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "517322d10863da715f2f3161ef6edb79" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "9f7ca941a81e84b40cf25acc53760dad" }, { "dataPath": "params_shard_181.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": "6002a7d97c1880f0397c60b98f51fa90" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 30345216, "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.44.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.45.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.45.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "2db6820b8e0d45be3b11873d115080d5" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "044c8eeaf1c50e2dada67f2f115cc6ad" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "e52bec6e279ffc677c455af756081af3" }, { "dataPath": "params_shard_185.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": "e9045c90da0ab11404cc997e19f979b1" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 30345216, "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.45.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.46.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.46.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "7cc94380f91b9068c0a481c546c7cd11" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "606813b505f0961365b01ae47a09a10f" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "58107dd504d46573c534b6209e95eb80" }, { "dataPath": "params_shard_189.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": "672a254293d47ae4cd97d1c8215f3bf6" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.47.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.47.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "44deb6697af07ef757c0cd2516c964ac" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "3dc6a057a06d58badedfc5512765cc04" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "6b2ecb57f9152ffae342bc4b766a1d3b" }, { "dataPath": "params_shard_193.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": "048a3d0c41a2d5b6af0658ee31edd44c" }, { "dataPath": "params_shard_194.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": "0c638bde45938aa12e7986965783a39d" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 28047360, "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.47.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 14745600 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 23592960 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28016640 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28037120 } ], "md5sum": "097f6191b8f0238720c291d6c99634f7" } ] }