{ "metadata": { "ParamSize": 485, "ParamBytes": 21092673536.0, "BitsPerParam": 5.000635812484114 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 131076096, "records": [ { "name": "lm_head.q_weight", "shape": [ 32001, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131076096, "byteOffset": 0 } ], "md5sum": "01d505afa223ff61461d1df12598d735" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a399a7112d398925e7bffacbfd116d6d" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "628c97130cece6f4d8550aec66654ee0" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 27705856, "records": [ { "name": "lm_head.q_scale", "shape": [ 32001, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384512, "byteOffset": 0 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 16384512 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 16400896 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 27673088 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 27689472 } ], "md5sum": "8736709b0737693c3c98c205688c9b33" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "122559b15711371a7ca95100ce59744b" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "8c48d386d07b92ff9af8ce4f9991068d" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.42.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8236ae6b08ca98ec31e5036643d2f64e" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "53b344380281874b66d152928105dd28" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "701b7e7cc27207b3c8bc3d12300c6aaf" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "d017c9ce95e6a149eccbf5b75194a184" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b4276599140e24ddc4c103b4100c2010" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.43.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3abb0e9dac9f1525dbb8163a23254c13" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.42.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "eb52d564073dab11e4a0b599ad330268" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fcb0059c65a3ede951656ccda1d51fac" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "926e904f066acd96528bda2be9d5878b" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "251819e18990d3f893232b79ae20c221" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "66e22448b1dbc6599a5e0df0d1182396" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.44.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "df0bca133200ac292021e96f1002a6f7" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d9e8cfe8610159fa59f8d4e9df63132b" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a3b0f4d70b20f6e579d4a7e74d7114d3" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.43.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.44.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "708c12f133f24f7710c21b72e48e6099" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "0e9c1c5a3302dc192e13aaa744779799" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "e571bfb9ddff35fbdd01e13b0e26d2dc" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.45.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b123ba0cff1eab9159d1427f9bf02dd8" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b83974f33a633d8429a2a73f7d50be9f" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "e7c103b44a9c080dc876bf5e05bbe53f" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "4a7334f1b4b5ace0764af149d371910b" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "64ee4361c2ddf5108ce2c2d54c22cfdc" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.46.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "796504efabd23fa71e5f48de584d881f" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.45.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "43b7214506f0595a12747af9c443a27a" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "041ac24956760160cf93b3fa08527493" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "78cbc57656393b36bb8974e3138d5428" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "a5517b523c72192c70124c060b4c2c29" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "56e79fbb4a645d14e1cbbc6ed906bcaa" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.47.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "11b2de3102a1c5974deef3097aa31e93" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4c1da83f7fdb07337e08025535411442" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 131076096, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32001, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131076096, "byteOffset": 0 } ], "md5sum": "c192dbfe22c4c074d7a126e819d7472a" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.46.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.47.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.norm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "6a69a5ca27c6ff55c9ea51b8fc3f8b93" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "e158180f2849f748fa011fc44cd1caa2" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "09726ac7cb64bf32d32ae3e5db40feab" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "657fa69ad800289b5497a559652d5f4c" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e18977de22a99a3267881208940d0907" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "40fe720528131cdfb3ad12c92fcbc017" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 32932352, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 32001, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384512, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 16384512 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 16400896 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 27673088 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 27689472 } ], "md5sum": "afafbf6bd2cebfec0b191d77c1b92954" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "242ae996c483b93e67464edd1a0ff955" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "9b12d90264a8265671b041ecfb975d29" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "fb1450b442383bacf6959e5fdb4cc585" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "93afb72c09011d6b1a8d1bbbd2ea67dd" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0a69b82c2a76e01f9bf87f300cbaffc2" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "7a4639ee730aae178038044001ac9233" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 24952832, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 4210688 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15482880 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15499264 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20742144 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24936448 } ], "md5sum": "135a4c485243d7d3810ec6b1d49f93d2" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "0b2f2379fff49069523156571d4ac6b8" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0243f597935e34abe868a6d7275fb668" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d47ddf690a24d07cf8dc94b4d3f5623a" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b20bbde7ece6d3b8c97fae6202e43735" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "8315a7f7cf06c7564f544f2ed32ae99a" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "296f7c3d1fca018713fed2c940905cc7" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "8b0a7b923351ad356709f20d12f4fdbb" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "efccd4509339732d3bfab4a21c5f3e5c" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "2930eb38a92ed0b306cbb9099a550a87" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "76ebd7841404e2f0f832d80464e32395" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "385fc5a3e6649ea441156a5a7c8e9457" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "7eff1b33a0b796e4fff982b3a6512c30" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0659fc2f65d386c9c8a36c82e0e9f1fb" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0e893f2be03368f565f7a1a67ed88d24" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e5a5166c56ec2ad16f696e3020d75ebb" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "09a54e9fddc2563a515c413fa83c0384" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "aecdb81fb75678465c58adb884abdc1c" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "33072156d2158c6657659d4957b9d4f3" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "5ce1627a4e794f77a37f0bc844282b7a" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a5253b02cc90037d699b315a0a4b8138" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8314ebb0b7261c7ea19ad99c3d21319e" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "63c4a276a124bb2c08c6af534aea3341" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "4373f33cb62aa887fff6a2f5568b23a7" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5b23c89de5f1b28b7a565dcd3a53f3de" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b37490fdfffdcb7e6e5f2116f6518622" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a5c1d9eb3701988bac56360b3f5cdcb2" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 30179328, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20725760 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25968640 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30162944 } ], "md5sum": "bffd3c2295b4fae22b7dacc913c00843" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "614b4eed4a26511a6baa542cba684102" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "4af1ce4d4fc4940846ac4db6d12246c4" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "78d7ee8e08ebad9399bf95a326677a73" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b1ca85b23499f666768e1eef192e9300" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "29011fa94e4ac77538b8f3f36aa1e7c4" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "6fa4732390bff094ba2b3302b2f6dcba" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "dfea4a3806fb154a459f4491da14ca08" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "76a1cc77f5d27f54a78c8984c9c27e5e" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "65490c0a77ebf741d6e79969819a5d3c" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1e725462e746fb2ebc9ddc0859b3d3b6" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "83d087e3cfb2e10a5dd84d0b3f1befd3" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "54e300dd995bfcef3e6a784f279bf80d" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "e9699a13ed0e76c028baab1aef5994f2" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "de74d76ec7eaef3651e8cf9ca328ba32" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "48c86f6730165c5f1422bf3f4e7ab4a1" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "ffd75f45c976cc4f6f31e3f63f773bee" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "dec429d6aa848ff1dbc497816cbdd168" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b591bcce60a641bfdeccb59cae7fc0da" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 30179328, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 } ], "md5sum": "aaf9597be48833dba13ae29b66ef96b9" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "117fa05301bbb6a88d3db6fb8e2bbf7f" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a8210febb76d9892740bcfb43c834d24" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "9760eb6b3346b6552028ce272391ce57" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "40297b7c07cd80468731d019f7e4c16c" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "294f9bac1b361e8b856749a012df31ce" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "07aecadebea5998b4da31f789e95c182" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 32047104, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20758528 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32030720 } ], "md5sum": "322844c6c0e4f069cb4f1ebe48c342b1" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ec964422f71503461be891118de68c72" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "9dd962857da354b976a431be98d94bf0" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "fcb6d815ffcfb0275f444b074d9d713a" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "93fe3b0fe8cd81640920d88b39a27704" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "64faf9f46e1023799acd912b7692a8df" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c8b295e36a0a48020af87386c3b924d2" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "e688a0339fc7313ee8092f795533f9d9" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "2db9a0c9d7a82d10c3e5674a073de178" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "6eb21a1e1afb645e8b40702e0369cded" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b95340fea09a5e610ce0f7800d7812d6" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cae1dbb48a927a4e5b59a12c4a9f59d7" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3d3c9cdf52412e8779ae77b50c94854f" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "7a82d9b56fa1df0ae0d493e444aaee48" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "7486b1cb92cb689eff0d7cd1588aa784" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 32047104, "records": [ { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32014336 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32030720 } ], "md5sum": "99361b936dfa2abeeba5e27ca838e931" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "b4db04593808a71eca28b3596937db84" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "be3c513879c1192cf4c7a31b144825da" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "efc1d747e36dfc1cbd3383777bc84318" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dbeadd967aa08c8ac2de39f24cb30ee1" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "e021549eb35e1ec664a4acc9db13c58b" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "7134be41b259e568a6c064e8f09483a6" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "c38b8e0152eb9bd6437823507db9e188" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "22daadbe4b9df32d5c2f8034ecbeb09b" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "55a6da22a2def10e7a153e37f4826768" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f19707d1e831bddb2389336e273e10fc" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "3396ddae6b9a3d278662447bc06e6053" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "7668e8d1455501addc7c30ba177c32ea" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "81e1e67600e4cb7b790ddeedbd0cf043" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "fc8d5ce72c99ee06cefbe6be204fdb39" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3474f0af00aa73d681f5e5f67644433f" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "c92c80cf34f5b80024c3f6dfeed52beb" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "b04893402f066e267bdb0636bc9acd30" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "c1cf326fd81d315a622bf06ace6811b3" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "835c237d0d0604f16e4c1578b5b4d9c8" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3c06be9803bdff4bcf21479ca4544506" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9369b4941d8c00141e3c25f076142ca2" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "599bba010760b6a71b3a35008d79e60b" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "1b109389f6f0ecbdcb32e4cc83a2381f" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "87bc5a918e18e35ccf89106bf7b61dbd" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e7bcf44cfbba4a2c9df153f8e9082582" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "b8665e0075b591a951f20f3e712fade5" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bc72b47adbc112d21682c3de8e8d8e34" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "9f40e21159e0b4510a1b5c7da485c016" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "783aaec219118c84524e13e2747e4347" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "eebc128f05d38bf49375030176ece770" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b0a442e130182a6a90fe8b49b4515746" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "07704f42965e61e1a89deee29549285d" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "12dfeffe1e88d1a2b7da53588bad256e" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b1ed11783da9365bcacdc45e10434042" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "217dd3bbf69b642e7b35f26b3f7efa3e" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 30179328, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 } ], "md5sum": "c8c64d1f3912bb15e8e4e4128559722a" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "eb7ff6e6f19557346a212e8940d19a36" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "f39e73a629547e8c448e7b245f08d793" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "749137a9ca66472673c2f1e5bfac04e0" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "fc4fcd35e860f7fa75fe29ff261a04dd" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "bd71c79263884114223e06607fea8822" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2194f0f049ad09a57827c544c1a9f354" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 32047104, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20758528 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32030720 } ], "md5sum": "b6da07ace53d80c5035f73c4319bbb6e" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a99d143e3805fca66bc87a102868b315" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "bea9601fa6b4e046d9dbac9a3a25f0ff" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "211bf62b351c0dd02ef9e1479c61ce68" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "28920612d2c0ac8a752f94bb8c77138b" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "fed79b42cafab89898f1b2b63cce59ad" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "011638179c96033deda98ef62a177f30" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "8600eff5448ea2b92ebdfe077810497c" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "375820ce05fae3e71354b554e0a0b231" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "8279ef868cf83142249037a6111c90ca" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "c35fd8652791b5a1e6c2d46ce3c3ff52" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7c4c4e0bd50a59f8e340d07690745f27" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8c0e90e7cfbd638efc7829c1e6818b85" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "45641efc673273650ec39e4b18cbeaf5" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "11ce4afa02730d31ff738ebe43a853dd" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "d67f117eb4480df5d3336d7ff34f143f" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a9f41ab4393b669f3545766e337be820" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "c0a2cd4a0cdb53666b61efb8eecb5c80" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "83abee75f732f63b9530535e5651a180" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a996441ee2290d8f9cf12aa496f29b7d" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "0cba39d622a14f292133aff402d22c0e" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "f6a4ab9332337195a214512e98670efb" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "685a0015f9d0fb9e352c4e13017c6a80" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e81cc5454910d8e91f774bd42e351bcd" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "08a1af1b2126914c09b49be0233b53a8" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "2eb95e105f359d7df183f7d69350eac3" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "2f81fda22fa7ba2f63384d7131eded88" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "a56b68476340bda35c1df5bf2dfec0c2" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "006641b37ed0361e5ce7a40ce3c43bf8" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0d19055e4b381a1f184422825f286f8b" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "fbd7091aadc55d8a64ea8458d18fa4ad" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0b5b545021e02a2ed8a3933a645e49e5" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6d512d086ed21979d0f61ae97b66d68e" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6c247655a42e6390d11b7fb9968fed57" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "3f4d890f599810fc478bd34e68ec9d81" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 30179328, "records": [ { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20725760 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25968640 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30162944 } ], "md5sum": "6e2a2cfd87c6fe13670130502f77732f" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "1cba9c098fff851bb4bb7898e1bbc7e4" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "bd510271c886d84b5c7ab24c9334ab1d" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0e4d516c3c0412098035e28bc24f9cc3" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "12ea3901bb9c1e84ff3e2a028e60501d" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3877fb356fe1b6e5a5c33456c50a699c" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "2005f34dded4bd4a116323474648553a" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 32047104, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11288576 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 11304960 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 22577152 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 22593536 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 27836416 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32030720 } ], "md5sum": "26f05ab5ce0cd0bd31dd90d10cb75c6c" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "a51b31e1da9155c56a1c0b4f1856baf5" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "bf75df46cace47f089ee41e6559afb91" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "bae1a799778d455a96eb49ef22769100" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1e9fd25870838f556926337c7b9ff898" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "ce97252ae12bbee2f9e8895ce68cb412" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "5f1f4ebeab7bfca905da88ca1017b50a" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "64cff2024d199be72685be3ad174c307" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "099f8c1eedee5b5f2032a962bd92c185" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "e78ff04ab596f43f7a7a3663b2e65bb7" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e294e1e0cd67fc201d40321d14a0bc45" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "3a85080fa44d57f63a7cd85bc88a4b3b" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "316ddcaefee1b28583ec4985f5925773" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "339c97e807a1b793cd4a83bd07fd3979" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cf0b1d62f367d0fdb458c1f36e7e6cc1" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1948c152b15e6bfdcda16fd653e0ab2a" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "00557ae4e30a1cb885fb4528edf1a144" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "c1e7edc6033fa14d9156491ab787558e" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "b41e2c586880882c26f33a15a8dd8a3e" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0f1f45b87f20df472ac620770d8ab78b" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5b89d05d12979260b0d305e750932cda" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3af66e47bb2113436c678d34e4097052" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "2a7af2470ee1a543b4f895c6869c409d" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "6516130f13858d92dccb9ee56d45186d" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "f0e095a67031214d1571625f731b1f25" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "326a979872ac56e904b037cc4846d3e8" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "bb3d40f1a1cb521b918465926bf70af7" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "75de239fc8fa0cd1d4ddf921520e6596" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "a664d562885300c3d40d8a9a25ea96c3" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7ad8ee601cf0febe8e0bf0e3c09905df" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 31981568, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 9437184 } ], "md5sum": "a689993a5a3fed7939c892fdaf2b2b9e" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9eaaf08a2c7012007dfb36ddebef7bd7" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a1b2ae3d9853bcb7768aa0bd7437ed63" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "28257d12276f79b6f011331b2e34f3db" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "035935c9626a8cef6660356b50529ab0" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "4276ad4bb574cf8e2babb3af6d2f2f2d" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2b53ac9a11d89ebcd66026c755e9fe8a" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 32047104, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20758528 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32030720 } ], "md5sum": "7b35120e4448396a1b42f13a08c60ec7" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "894d2236be4fd660e329b39414e57ea4" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "c1482184275779dfac2f79ab00b75106" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "ac714a2a013547a9a775e5d1ec8880f8" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "ee6ff22774a1b9c4dc0978d18aaaf771" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d4d1a57f830da2c7211d818a0b887d81" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "61dd81a2642646f600a82600889b1e19" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "d6b0f8d2b93db459dc0935f756e17199" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "b3804fd5d703a60c0749f972e20c69d8" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "2a750f38946683eed122a3a25151db21" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "7df72c6232a5d44ddc4cdefe80c92cf0" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7e7fddd9639fc36d4e20e2f6d140ed21" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "35d4b42bc895987864ebbc1987ff641b" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "e5724255a2b2a541e6c919e1a1e9e519" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "f71d4cf48d1f96013ef5bc0a6a07f522" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "9179ba13ff2ccfdf57f97c85e0d07cd7" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "fdb8381bfc387ef807b166b3abde538d" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "4615a9606506aa1c3f93e2e2563ec98e" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "65cfb3e2d29bd95c5aa99b1000dea6ab" }, { "dataPath": "params_shard_259.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "fe21df95726c3687d631cf6594f23ab9" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "d22e1716b5b4976e147726285f3a36a8" }, { "dataPath": "params_shard_261.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "46076e7043509a9636df0776b0cbdc59" }, { "dataPath": "params_shard_262.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "eeea1566a913d0b0b56e8ba8910a70e5" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9bfff3276fc5949a8533e64c810555a6" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "d07c1a9eb0a80fbd1826a8cdc43e1bc8" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "ef46fee4589c938cc3646ba9b60a3b82" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "45c0378162f2c6fac35f2743488b06e7" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "182370a4235a8067a5867152ce0f6d42" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.40.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "69de1cef15dcc5c9c0c1220daca99b6a" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8624f0f5c3973c6aeac9d0ac752909ef" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "177e49b72df40d231b859d615d486aa8" }, { "dataPath": "params_shard_271.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "d338265b592a0c4d0d4efd6742bb0cf1" }, { "dataPath": "params_shard_272.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.41.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "34f7bcac938a9774e0b410b309d8bfcf" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "475552c85effa69472b7d2308ebefe5e" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 30162944, "records": [ { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "bfloat16", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 20725760 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 25968640 } ], "md5sum": "c21291609bd8a6e42545ac8b5c84e8c0" } ] }