{ "metadata": { "ParamSize": 325, "ParamBytes": 4077395968.0, "BitsPerParam": 4.500422426883416 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "lm_head.q_weight", "shape": [ 512, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "cdce896e69a0bafa0e3062948e7250c4" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "7a0cb5295a487b90f342e5df2d2bb247" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "6ee0e06d4af284b4b27c22d3d2d4cc5f" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2d25c767fc8f97924ae29ccc473a7717" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "840537498aa086338f01cabf78a1dfae" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 30441472, "records": [ { "name": "lm_head.q_scale", "shape": [ 128, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8388608 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 8396800 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 12066816 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 19406848 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 19415040 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 19423232 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 23093248 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30433280 } ], "md5sum": "144b699344f0ccdb03f7076e88984d97" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9b0867380b29f20bf7c03535ec1234bc" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "d8f44c28f0fba4673de46d97a8111e2f" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "4909faee1291e0ecfb027327a36c6e05" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "6ae30c20efe182970a1d27b34b43151a" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "cf3ca40e7451a3fe0ad15ca5712d3d4a" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "306a5eb12f02036d6519b5e1c447041d" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "e2442d29e06e824a3a0ab1ea9efec2b7" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5eaadef5bed4a407b5bb76aa87011090" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "eeec3251ca17d7105b1826f5bc47d448" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "2f867ebdddf95ca97058c052681a565a" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f62fb9d8c7c541cad137345a9bfdf538" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "506e1ca5530b37650e89c2c8a5e52ffd" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "c49d24d4b2bc9a1bf1d3983446ec78d7" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8ff24b1115155b0b0e022b823a00927b" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "ef7dba1e939a9b1560db69062deea5fb" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "8b8870cfedc751f6d8aeb2b4fe7d4ea9" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9c0f5112e3419ebc2d89b6ddcc29d32e" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "bbe7a78948a367a0e45eca441d9d5d93" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "35f63b5708ef62a6d84d0aeb906c2eab" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "d17bb894063a9380af67794216661ea8" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "422ce742bd4649c929e4a9130bf23b4a" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "16a9e2559d220c6fb68a709a2017bf55" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "8a46355fe722a30ebca4405cb5e404ac" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "08a86ee2a82dd41931a402d6f400be0a" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "26ebc9e18b25c8f2d92d7247c775011a" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "2bb2da606c1eba25c8a6ea6e1567e35c" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32768, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "6fe56e3dfc342731c11bf46d1c673866" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2bdac49eb8a57a381283cfc89968de80" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 31997952, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32768, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 23601152 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 31989760 } ], "md5sum": "af8433eaed6e06893d59eb5a230d2295" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "10744e1c581eaead568976657c409a16" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "8763f87264ee5289c0bf8fdabd877947" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5fd7af5631dabe1a4d0bd6fc415733ec" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "7d33a724ad46254330131c32d1cf5902" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "6b2a556b07de34f748d8a4021f42f74d" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "6b1d035d67cdf9f60618c476b37922e6" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 32505856, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 11010048 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 18350080 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 30932992 } ], "md5sum": "168f691544178c079691528b87aeee9c" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "29475d38e9f368aa21a72a5ca7087796" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "5e4af5c8a5cb926a59c97ed5b6b51175" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "e504e240dc35a8739fda35945afa14e2" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ab36d5935b7716980210a56113f9f48a" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "e1e038dc62c000fcdb2a9d7874667605" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "3a8af383a2029af545aab54d65f8a1a5" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a420ac2a4e2ef820003c1d306e62e300" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "663744d2da3c8c77e70b4e22a6d22b9e" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "7e582be8e51107494fcbeb762ad366a7" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "6eda83e630484d22a934da7e41535fe0" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "4a1e8c09c83e877b672c08af65610366" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "81fd97fa48a967d8a3d407e2355bf81b" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "fa035a73d58a03fb7da051bd3b3b6fb3" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e0e76b93b460b0cbdb44876353e6f9f4" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "2db4d1a4b5588241556f8ee85dd55d19" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "73a2c58e8afcd9e03c560594bbd5443c" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "1845e571d938293072da03a009bb81fb" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "621157ace2b7b4ff7e7263c5de7b6cd0" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "56ce854eb30c8ccf6041fe43e25c43ca" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e70a586c2cee083eba763859988112ba" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "f77f12646612e91225842c4fc47495c8" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "906633967a9e850127bb14c55b028b5e" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c3b362f5ccba065107a005465ba18319" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "02aa11627ef574899ebd4361f283c13f" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "17202756ff682a0482ad50f12675f2ce" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "db2a9e25699d48fc7e378ba1ec534df5" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b744203f81a29b5d9b29907c5d655109" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e786ab894adea73f7611c1d9ed6f09c7" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "7677a478cc79510e940262f06d8bd9bf" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 13115392 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 13123584 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 13131776 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 16801792 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24141824 } ], "md5sum": "3f1262aff102b6d5f075e48cb90e52e1" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5694f8aa8d9c525e788ddd168bd07c8a" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "de951d9646199770af8ed54a7a104059" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "4e75894263a4a511fe5b8a43fea1c49c" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "99015b89abdac2bde86122616722aef6" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "58be3c124fe2710b34b8ddaf2cce166d" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "5362661e67e1e3acbe952a625a6b0ae7" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "6423ab5096a6f35f7512d03c72e90796" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b3e73984972e2374b8be6d4e2136c28a" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "65c48b3417f987dcb4142269d6a0af08" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "ee1a12d17f95ea342599d071516c96ee" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "7b5d7beb83bc408702860b84ef1b15ae" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "6527d374aada7491766f72b065662385" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "c2bbb77fadd2475793ee36f1aac2ede8" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4a48024d9c6c9215e04ad388712cbedc" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "e82e4a880b07b5f05becddda2a1303fb" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "7170cd5067e92e8adb003f85e8b57b7b" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "006a278e6d098f4ca5fcf6b3e52f208f" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "31f33364f6eea1e06ae876836d1f269e" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "f06c66c86d08eec4428306a227a58d0f" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "462fb70dd77dce712f505367997cec97" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "095d6d8e52657c236c37c5f99d75bb9f" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "eb44d924afc125b1539edecf07ef3377" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "273a2a7ed1886eadd1f7bd6838fe6561" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "6995b521f54a102542d2d6b7f84cef6c" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "a49a19aa0c6c0e93c1f15af4ee2c4bf1" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "3bbb51750ed11d32951d227d9fc2f9f3" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "abc78bbecb9410e7e43182c0a91c939d" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "a81b121e20d0c9408c8974699960dae2" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "d226c55502b2cad13741927dd50986c7" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 1792, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ed5dd32a71d91744937b6b7850bef657" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "0c5a42d4bd8ca1ac5b23385c708ef06f" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 512, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "6aec7d1f6bc36b1d00f99db34095cc1e" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 448, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 128, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "f254c8603596de4ea7580c94d3f7b83d" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 33030144, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 512, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 9437184 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 128, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 22020096 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 512, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 23592960 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 128, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 31981568 } ], "md5sum": "7f422e989a2c2709cbc4d4b2c2710f6b" } ] }