{ "metadata": { "ParamSize": 325, "ParamBytes": 5019975680.0, "BitsPerParam": 5.000895144643644 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 262733824, "records": [ { "name": "lm_head.q_weight", "shape": [ 128288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 262733824, "byteOffset": 0 } ], "md5sum": "bbb22d5fa09313e4041e9082a8dc2091" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ba3411d7a8913340e007469823407b0a" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 32849920, "records": [ { "name": "lm_head.q_scale", "shape": [ 128288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 32841728, "byteOffset": 0 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 32841728 } ], "md5sum": "b0666da89542387ef2419536b2e72826" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 262733824, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 262733824, "byteOffset": 0 } ], "md5sum": "18d07f868e83271ef160e81ce61221f7" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 32841728, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 32841728, "byteOffset": 0 } ], "md5sum": "4085f7db5d694400f6d326393d77a2e4" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 33054720, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 3670016 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 3678208 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 3686400 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 3694592 } ], "md5sum": "4013e18b1a221b52e35724c023b8aaf1" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "418ea9f91f18ca941f672eab13208f4d" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "e3ac15bd9dd134232d48148ba4ecbfa4" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "d72be350fbbb1615c13d15957483c035" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "9c65c031e7f18984327eae996e6250ad" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "79e93341cfd4e5e86bfaf0596fa8f802" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "92b8eb9e351bace8004bf34c8b9f19b3" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "d98a5287f1d5fa6ffc1371efd7467955" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "e6e8a6e45efb81e652cf0c6ebe2cb604" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c0d5d025f5a96044fc914275dd2ad598" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "c8cf1eb31633535dcfec9849784fe054" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "61de77bf36496be3e69537e727bb1a41" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "371043920b2df0138638b780952a69d9" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "90c1ceb2955a71a78499bd78adda7d69" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "18bfb969319a7789d18b8517537225d8" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "161c0463ba4c8e935b6426d20d12f917" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "065c3cd79bd71727c824b182a87cf064" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "ee90b18044124b063d28f3b671d289c9" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "9b7f569a0849d09844cab060d83c269a" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3b62ef201075e7cabaf8d3050e3491b4" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "417ba9088d1bcf75ed26ab8923f7e577" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "1bbba8723bf2127b04549c07bc195ed0" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4c855c8b321cc6474aa47cdaf1a34fc5" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "79d45e8bc303c4a279c667116b0582cd" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "6b447d3475cc309c87445adae2564bca" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8e4b1a729a85cee82e9d4d7626ca1e38" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "b3ffb04b2f58016a8a8a88d4240ea978" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "81c74efa256f832d93998b1f9a4ccf9e" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "cf2301c84e9b254bcaf7068d734b3b50" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b603ed3432ce3da1829c261949e0c56d" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "51a5e96e8d1d8c67e0bdbab64263e332" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "0a36eb640e417b4036c21d9251850ed2" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "93213c0bb9c9e976d0c29acebea6c4bb" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "ed7aadcdcb53371438d6cebcdb381479" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "f146558378576a15336460f17a8c8005" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9f462008b9fc9ddbc957c15a251da2e7" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "37a9fecfbae50c7c65c6cc399f7b2723" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "93fb48b788ddf6a26ceb49baa8f3c5f7" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "fdea9b6d74ec5b85c206acbfa779d751" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "f1039e97a91074eaf4b575e32a54368a" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "0470c1327102a78480b9aaedf7aee810" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "c52f1d48a3ea60f7175f9984da63d969" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ba16b121c64d3cec0241d67b5ea63a3b" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "2583a3588f1aa74aabb82dfb5d028132" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "15dc658aaeadac41f0bb3c74afa4faed" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "66b56a3b63f58e3114dfdd1d4d78a481" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "aa24b796a63dcaac64cecc7f4507a1d5" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "a4e95277b0621bcf5ea7dcdf3dfd6f8c" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "462708f2d8aff57be2610de081b67a4e" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "0ad2acbceedaea88e695e0db1a70beb8" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "db53dca66bf5d875217903b09456b4ec" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "07695181660c0dd258354e9ab296129b" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "752f656082beaf08edc4629e7ec0a337" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "bc4c08f458aa099079e94efefcae0d4b" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "fbf040d0c76d298e3e6f2731d517e037" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "17c19af4752fdd927a8c975e6595bd95" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "e567ddcca0c42383de1115925c86fcf1" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "1354c0fa0eb32cedab4c4ba9cc05849a" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "0ac05f0022ec35f4d16e056181cbdf2a" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "35476a0e3baacf0d045b50b86514ba01" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "26f203f903ab97e26a8966675404ac8d" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "668bb45a40ed08402f0cfdeb4425168f" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 30932992, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 23592960 } ], "md5sum": "ba1170c39efee6adefb5454ee523b39a" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f7d9f5418bc69e1664410bd07ddf8999" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "df362355cf7be79a4d6ddc472c6b5ff5" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "e39de7b1ac20634729b07c771b460d14" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b5e57019407afbf9f624279a8da6850d" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "3134865e6f9890eb03fa66702473d438" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 3670016 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 3678208 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 3686400 } ], "md5sum": "e25e2a339518734b6b37fc3bfb1d6d69" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "8205f3b80d8d631a651d09b1dfc015b5" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "7d40c7a125f569ac4b4520d8616aebb7" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c496df7e1f4b0f0e9f1daea8066e0a46" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "51a9c632a15bf531f4ed29ed364dc138" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "3ee38c53ba69544134ec8bc83a749eb9" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "045203a83c5e271f8e065f7cd17d7a1d" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "3ea375cd8ffd470f03dc83d3acb8d552" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "24a41a3a3303b468cc6f948f34e8f157" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e726f3d372bdd1412e0d2dd31b9a623a" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "479afa4feb7e2619f583980ed75c0511" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "3a10f546f7128cc56960773c1595c22e" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2caf2bf267115e2553c47c1e918eb592" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "226f85dae2cf5c3cf058bf6d05e11ecb" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "dff8b3fbd6ea0cb136196e0fcd0fd693" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "cf1419ad3f1104ddd05c909ec8afe846" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "0b3c05cc1c284b0cf7b4653c410665e4" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "148a67880cdc1cf42d3380c5ddd75b38" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "51bb7a8c144dd59842884c910dfd3cb6" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "120e70701073708457ccd2f37aca0530" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "06e91da7f153a0a2ec834882ed783751" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "128fdefcfa5ce74bff23464207a5c74e" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8d34d37803d5b5712ad684b032d45f97" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "dfc83e6838d127ac83a3962bf7ef633b" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "516f8ae3c0ab80d0918d22fb4df5f737" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "de1476951763833f684f38f914d32400" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "3476a1f784d3b5aa78d300e35081a4ff" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "c9f9df6b57989052cd3704023b79e4fd" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "97ef05ba0ccd462c3427652e80201367" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ec4152f232f36b53ef1c6185db0ed73d" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "5e596766aa1639a031d0e8adbeee133e" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "c4e1680f14eb3f5374a63d075c4525eb" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "d648edfa4ef71d7163da1ee3f10fd370" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 32505856, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7340032, "byteOffset": 11010048 }, { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 18350080 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 30932992 } ], "md5sum": "ccb1933c1b516b9a64d71e2a00f40a19" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 9437184, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 } ], "md5sum": "5e91c2cbb1be95538bf27a43b04ab2f4" } ] }