{ "metadata": { "ParamSize": 805, "ParamBytes": 39688355840.0, "BitsPerParam": 4.356224340918386 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 525336576, "records": [ { "name": "lm_head.q_weight", "shape": [ 128256, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 525336576, "byteOffset": 0 } ], "md5sum": "478ba82a33942a6ad70ee42e8fb9c629" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 65667072, "records": [ { "name": "lm_head.q_scale", "shape": [ 128256, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65667072, "byteOffset": 0 } ], "md5sum": "fdc92413dd29e9ba807757e02d8d7824" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 525336576, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128256, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 525336576, "byteOffset": 0 } ], "md5sum": "14bd89a96e685b4aabec3b21d76475a5" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 65667072, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128256, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65667072, "byteOffset": 0 } ], "md5sum": "fca0f406a72aa344dbce3b9c2ebf3597" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "1f48b4c026132d289dda1518e385d475" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5224118d911b8bc6482c000474f9dd34" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2fabd7dc21444e43d875e46d368ab284" }, { "dataPath": "params_shard_7.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": "a2fa07db651eb4527680402f54c35192" }, { "dataPath": "params_shard_8.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": "5e589c315ff8cf378226911332cde954" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "3a179d63a580c6234be7f930c040d24d" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8ef433592faf835c94eaa639d2fbb401" }, { "dataPath": "params_shard_11.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": "e58ca887e31e80723b84f3e8eea6a893" }, { "dataPath": "params_shard_12.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": "aeb94046282fb99efdf1a0a86678e6d6" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 16384 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14696448 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14712832 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19955712 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24150016 } ], "md5sum": "eb9aa591d9706115ed672503aae547bf" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8f43cb831b4fd83b1e54f1c9abf8680f" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "97002b06e36e47f4af1a64676ec6c781" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "fe1d431860c523bdac07bfbac5d72607" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a02df41118992fd83ac47cb2adec04ba" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "80cf21ce3db14cd87602628b118f31d2" }, { "dataPath": "params_shard_19.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": "a01c9b9222f0f99890a31d2964ecf003" }, { "dataPath": "params_shard_20.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": "c6341815445711578cad2475bd3281a2" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "bf5f6a2762534babaee6002b7c5e4981" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "c639518ef7ca591dd0ad5482c80cb1f1" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "577798cfea1a00f9f90b103d3f77ad70" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "00ff10fa5488eb8737c8ff27c67f5078" }, { "dataPath": "params_shard_25.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": "b3ea51ac7cc4c2d4cd081923e0618cf2" }, { "dataPath": "params_shard_26.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": "a3b86cb4943ceb97ceafbc83c9025db8" }, { "dataPath": "params_shard_27.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": "467aabb5a45fc2135ecfef2baf1304ce" }, { "dataPath": "params_shard_28.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": "0f97f40e96863ceb764b8b860aff4ffc" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "460180eb0088df354c6109933e6d0a8f" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b4690d8d5e7a206f1e96e08e49966089" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7263c2a92bc62523b2a1d96b0f94ae71" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9a0cd0488c3f84ea7dd8efc3273342e1" }, { "dataPath": "params_shard_33.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": "96f57971d96f44daf00ac6d28235cc81" }, { "dataPath": "params_shard_34.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": "ecf40a0d2842251461b9ef16b456a4dd" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "745ae47f86b58838da914a852359da1d" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 28360704, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 18907136 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24150016 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28344320 } ], "md5sum": "07745b2b534bae526a48474e7f953b18" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bb8a9b88b6be437ba344256f61031e1c" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c196ef174d2371e3d69aed5407d332e1" }, { "dataPath": "params_shard_39.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": "cf8cde1d3cff64cfbe72f8d09c28076d" }, { "dataPath": "params_shard_40.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": "36930f3d76ef0887208e5e1015f88e44" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "1af4805c4447d2ec8eba696fe25c52b2" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8869c29a47950cb27e7c9fa8fb794d87" }, { "dataPath": "params_shard_43.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": "5956065ad61026f52eddac92bfc47da1" }, { "dataPath": "params_shard_44.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": "f2357110a8c7e822388d5a342bcdd688" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "3f90a03f78a476df37688f9c1d8edd3c" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "862e2b318a696a047df4cb9943540982" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0c9708d4d3beb021c6e719d67012d3eb" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "66046cae8850f9cee23128dfa81f9f78" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b4b14e208667a21560bdcd87973f12cd" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "da0e2b46da0aaaf95786371416056073" }, { "dataPath": "params_shard_51.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": "9efc3a2d650fdb72eacfcbe48a3728f5" }, { "dataPath": "params_shard_52.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": "5669f71839830937bb3116d7fb539be0" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "17e91c624b5d27d4e74d19cc1aeb9d6b" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "cd0316639593590bf8da5ad779061944" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6a0fd8ef49748614f5abaad65fd5403e" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2df32e1b0e9d9d55c7fb2be6071d2ec6" }, { "dataPath": "params_shard_57.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": "1ab54fb942c2d1061348be00699cf432" }, { "dataPath": "params_shard_58.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": "b06c9d90234e921fef0be15e51b8f84b" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "209968c960c478c17c36bc5a116e18bb" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e5bd4cba4bbfe61ae61c777e01bd416e" }, { "dataPath": "params_shard_61.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": "701b92f89e57b90e3b00a06699d61ed3" }, { "dataPath": "params_shard_62.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": "692e3e23352560608aabf14eca204eec" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "f5219ddef7280c0f3eee52164cbcbd7e" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9ff444fdb579464b03dce77fd1df49c9" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "a79810deb4ab08d89ec7c16fd103e1b1" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "8a981e51209b3b66837faf8d48a11c68" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9eeabfcda2274eee752aead92e01a716" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "67600ff69f4e75c4ea18befa2452c6a8" }, { "dataPath": "params_shard_69.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": "e251ed888cd588b16a795833f4726986" }, { "dataPath": "params_shard_70.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": "00a5871757c8e1f6133750b60b68f1de" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "1d23f2fb33a622cab2f3251e2be21f48" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "e43243cb26a563649d1996eeeb39348f" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c6afb8a967cf418afeead1c7e152ff24" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3a76cce2864e928484474e1d9d5e7705" }, { "dataPath": "params_shard_75.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": "058550cb7c768be0040146db7e2e59b5" }, { "dataPath": "params_shard_76.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": "d8ae58f3c1f6d010714533d8381cfe13" }, { "dataPath": "params_shard_77.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": "de2371aba3377cb1811181371bb29f0f" }, { "dataPath": "params_shard_78.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": "6b8d47b154a4bf3b07ec12e51256519a" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "c5257f5fc17674b340105889512905e8" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4eeb1d95e7876be7079f6469f475fbe8" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "3ec5269e628312924a53235bf6e6f0b6" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4a34f21a1073405749dc1a2534309c26" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "7a08b3be9c3b6d575b9ff371d341532f" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "1e0706c47185aa705ddb31503617105a" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ae2a599c2ef43422300713746586d7b1" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3b2a4c5af5b17aea14b347f0731988fb" }, { "dataPath": "params_shard_87.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": "08da37471a2438f23db68ad67d572de1" }, { "dataPath": "params_shard_88.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": "4bf8cb6a6a29f468d9dce35c3ef30e4f" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "41fa9674cca17690c288a833ce8b825e" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "deb99267bf3931128a2b88533e0a790e" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "116849d108445e9887bdb4e932230f10" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8bbce71b27c8da54681505d3993176f1" }, { "dataPath": "params_shard_93.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": "aac2ae28c05cb864db7258354689f887" }, { "dataPath": "params_shard_94.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": "6f05bbf0e7fa9f6b2dfbf9a2f454c355" }, { "dataPath": "params_shard_95.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": "34fa003c2e52823df6fdc20282873243" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "be7bf1030ebe701051d0a14d23230884" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "84efe5577413aa2e74b8728d47ca487b" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "083808f910f5df2f51a9ccbf7b3950a2" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "dd57959c731aec9b10e0150f062168e9" }, { "dataPath": "params_shard_100.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": "3483649d0278247c6364bdfbdc05136f" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "722401240f773a477b4662b94327bf8a" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "f0d3289d1b50d3c0cd03a959ccd49bac" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "0a4a717564d9978b88f9eeaed48d10b8" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3d72b4760c003bfa012f10c864831b67" }, { "dataPath": "params_shard_105.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": "1fb9e2d10b3b5dfc7ccbc0a407819552" }, { "dataPath": "params_shard_106.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": "748db9556faf802a37b69e1f00201a48" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "00f6750954313babf42cc254c94ec178" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "58012bbd0fae88d70f40007380dbbde2" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5b8e93f9b197b75fb21818558afa2951" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4ebc7608cc606a063933d0e58925674e" }, { "dataPath": "params_shard_111.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": "ca90be5708f52b68042cd42e6e24d763" }, { "dataPath": "params_shard_112.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": "1cd75eaecf9a1ec3c9d05f7d2898b09d" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "dbb4fea35571613101cecc37342f706a" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "2993ae77d8a6622ad515601f02a6b967" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "1fc50351a5dd4c5a4e0e8cc4cf8054f3" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b6d09f7755c46f3d68153053fe17aedd" }, { "dataPath": "params_shard_117.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": "09e52d5e57461eae9a94ca041a3141e7" }, { "dataPath": "params_shard_118.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": "8faeb8e35ee614dcc5adf77fed2467e7" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6e91f57f93982a48abafef05fdde5eca" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "7dda1d62f2cdca5f9a8102cd4031dafb" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "120aaba75daf75f982aa3f136fd1a598" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4bd92b8efb91e0bc0725e28d4b83d9ef" }, { "dataPath": "params_shard_123.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": "e1753ddfbef5950ddb6e17971da0b0af" }, { "dataPath": "params_shard_124.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": "2434d3e81579621e430c4b7bbcb6480b" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "fcce5c1068fce23a481293507387a980" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "64c6fc29e0fad1684a65712f4b0d6db9" }, { "dataPath": "params_shard_127.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": "8e4ebb49b29b9ff16e6024451a902894" }, { "dataPath": "params_shard_128.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": "ecceb1fd6e2f4447c4350d7dc9d14f1a" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "f8277fbce41ee7af978bf1c973d06322" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "a0d99b1621929238714d41691a46a532" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "073b39f943891f8bc851603fd91d126b" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "7ec27f47783851356998104b6a01e340" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "018964ce2d8d72daf38270a2b196b797" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "7761941db68e68c5b8b4a2c3cdd008e9" }, { "dataPath": "params_shard_135.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": "9da1f8434f1cd234adf4047096397362" }, { "dataPath": "params_shard_136.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": "67c535f9dad12a21af6954387583266b" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "418d04b1c4c5db1e2d0cd0c29bda3b87" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "914f3f783475b4695656ed18e6069235" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f00a4fce536888643895d48e5a0c0fbb" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "7288af9c13c140ceb25789b5001077ec" }, { "dataPath": "params_shard_141.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": "17ba4bb3e604ed455b21faa051457f3c" }, { "dataPath": "params_shard_142.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": "fd2e8a2006e565a6cb220c2405495eef" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "53eb960630e0dc1783b6783b02b332bb" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "99f9460797bf14f92e6cd2b01715be51" }, { "dataPath": "params_shard_145.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": "280dcc7693590a9bce0abb23b228ec51" }, { "dataPath": "params_shard_146.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": "5df26b669d0ca925795bd2bb12d11631" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "47c848c4488aaf043ae0689ce4127c78" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f441f3bd9a118c05af100f918fbbe759" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6a864f1c69ef569a223a618efd98ab59" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "9e117804b10e128350302f76e57f4631" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "581c772bf4ad5b694de9352bee48f583" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "596633508b23d18a418d651019d4e574" }, { "dataPath": "params_shard_153.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": "a90f4c7c66cd170489f4576419d70eb6" }, { "dataPath": "params_shard_154.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": "9b56a5bcacd0654a02e040171110f0d0" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ab160f62321d79144abb97ccbd6d19d4" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "9528c225c802fc369a63f337e3737fc0" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "dd91d56435dbefcffdb3fda44293d0ff" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "09568a58ce81bc58605f6735f5c4fd4c" }, { "dataPath": "params_shard_159.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": "58d3690700adbef510c70506c7aeef87" }, { "dataPath": "params_shard_160.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": "5be50d69aed72efa056a7f27de061624" }, { "dataPath": "params_shard_161.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": "7c49df8eb17af716f959369c665b2dff" }, { "dataPath": "params_shard_162.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": "c50045a98ebb445351e5a71f561235bd" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "a9d9f495a77a1ca182ecacefd50fcaaa" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "a38d1bb0d1812291e7d541bf5959901f" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "19c8a79ab49dcc781a822a4295cb0b13" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "d23ce4c75c279507bd4ce7cc6895a5c4" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2a46ac5914e75ba14dd595bf7e5db1ef" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "2dcfcef4214d595c04dac830502878f9" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "86c4243cd19ce8a46df49c44f19868b5" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e86186f308c443a164551d0963442f8e" }, { "dataPath": "params_shard_171.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": "bd0915dce7f4bd96331592a5c2ce25fe" }, { "dataPath": "params_shard_172.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": "1d216cc9b2bef9a3fc4af875de1c98e8" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f3274dbb567c77015ef419b97de4fa2b" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "6d4d42159971b1c6a06401a701fe835d" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a570722e9d7f43a0d31f6153fac4cb55" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e784a31bb7ee3734a8cbf447ab09d236" }, { "dataPath": "params_shard_177.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": "563c9a7c6487d123575166a3a229b77c" }, { "dataPath": "params_shard_178.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": "657c2f606f43f1ccd350756a8da72626" }, { "dataPath": "params_shard_179.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": "6b4b7d4786f7be91fcfbe9c1b563d538" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "689d594ea65cc6cdac62aa99efcd8b30" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "acc2a964752b4c7c1acb6fbc0af38fc8" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "86a0ab3a203f278c8512084d2cf95ec7" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3d61712b027e639bf5a383202d289cde" }, { "dataPath": "params_shard_184.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": "3c48bbbe765c244da5133866fe1bdf50" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2eda07cc79b1e65873040ba41aff947d" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "225bb284b21c6d8e958803a3ef1080f6" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5cbf7704a5eef88fac4ceb12090c4892" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b6a195eb2a81ac53d328005f8b54c056" }, { "dataPath": "params_shard_189.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": "597bb32af314086c1e138f1e30c86e62" }, { "dataPath": "params_shard_190.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": "8a5c28a16fa43e3cdb059180ea9289b6" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "97b0940dbef5bd00ef3b21cc2e81a591" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "aa159e85e0f32f3019949d19b923c0f5" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c3f1b0c9fb150df382c4ed2a679129d2" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "705af047f4bced5ca86a44a6e83b9619" }, { "dataPath": "params_shard_195.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": "efc151050c1abc8b8997f863508b1f74" }, { "dataPath": "params_shard_196.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": "803c497035d5e93aa5b347712beec4c8" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6453d895e12e1d79903fe023a78769af" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "078cae7aac20ace78b64ae9aed562aec" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "43fd8889a2ec304b2c040fdbed216067" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "aec41f866e71f2f587740a4c10484e6b" }, { "dataPath": "params_shard_201.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": "5850ab4b5cc4944acc7546c343d834e7" }, { "dataPath": "params_shard_202.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": "4513ab337297e978ef8dc16f9e1f2b28" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "447f09b7e224fdf48b8da66ee84ba249" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "7c9a48bfe145ae040f05e3beb43fca3e" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6da334800c1a10770f562b8dc8fcb1d1" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "aadcbb481c59f1e5ab089003bf332828" }, { "dataPath": "params_shard_207.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": "986e61e47d9c424ea76c3f57bef2261a" }, { "dataPath": "params_shard_208.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": "6284c36a04ea963b6481666e2ef172e2" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "611a43da0f37d5a08e5ecee62a9644ee" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "0239c3e369ff6da2d7054d461bc20282" }, { "dataPath": "params_shard_211.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": "4633edeec94f7449bfdf72f3cb312636" }, { "dataPath": "params_shard_212.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": "cd62566ece313361d60ec96ac8ff1516" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "95ba62b1d6ef06a4338e140403b2e418" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "312d15fe8943a20b2b9e190b287cc691" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "cd85815c081365537d748bcd69fe6eaf" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c44d4a7008cb8a11a5d7aa6f6aa619dd" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d9df3855fde1e25f451d5bd6cc979da4" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "9b2a5daefd4e57bba94ce9afe93e2e03" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7f7a4e61fc9fc4ab6c736241e3f3797b" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "610b8958ac210cf110d13f2ecb95c646" }, { "dataPath": "params_shard_221.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": "8627e5e3fd1ff22c3554ddc16a1eac97" }, { "dataPath": "params_shard_222.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": "502a2af874a88056ded5238a7f553757" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "a223a8282810229fa631907cbfd8a0d4" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "b713c990926afb9280389ce96ff28649" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ee60eef2440ac2c91d05cb122591d84b" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "392ce9f415de35e5ebcb49eba7b1cee4" }, { "dataPath": "params_shard_227.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": "a69965b8177b3e45c0c6012b89ab69ee" }, { "dataPath": "params_shard_228.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": "ca16d3f0f37798d05983647343d46483" }, { "dataPath": "params_shard_229.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": "5f5e2ef42a48d61496976bce132ef7b0" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "da603b0d53296a6fffcb059e79199f6c" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "85b901b16e4c144f7f08127b8700830f" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e0b699ef5cd313d74e2ef0d5b06efa8c" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "15ace8f934b32e21c4e64ede2792f97c" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "27647c8b4d4b1d2ebe4e339c9be24bff" }, { "dataPath": "params_shard_235.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": "2a117a6c33e991ade9fa5eaae95654a6" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 29409280, "records": [ { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14696448 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 14712832 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29392896 } ], "md5sum": "26f6ec958539dee46b604e191af66830" }, { "dataPath": "params_shard_237.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": "d08318fffb352d2d5e4836ab753d933e" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6ae89299e548251c47a14d03b8ca4331" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e3cb5f0063faab8af0f50c83d2f1cf82" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "6c707b23d871e36ef90928551c90e92c" }, { "dataPath": "params_shard_241.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": "279b7685fb2c1bce23a14054be763f52" }, { "dataPath": "params_shard_242.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": "82350aaffe13c2f92f52ce1ff141fd15" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 9453568 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 }, { "name": "model.layers.42.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24150016 } ], "md5sum": "603c1dfcc04a16793f67df645ece3186" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9b9bda85bba5b9d1dfaa24174b0bde0e" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c13902e118cabef8b3c29b03a919c40c" }, { "dataPath": "params_shard_246.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": "e3aee1c46a4d55fdc38e70ba1ff3c236" }, { "dataPath": "params_shard_247.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": "cb9b7213cd3880adc4ff787b8b985893" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2d9b3d726fadb01914418766d3059810" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "30649fbb5ee81b104e34f440828e9f56" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 28360704, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 4194304 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 9437184 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13631488 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 13647872 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28327936 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28344320 } ], "md5sum": "a22f6a80d3bf72f17e4bb05cc00dac89" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "925e92485572f02501fa8df6ae823e84" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3b5e0f386c459f6d26847b5fa50b0bc2" }, { "dataPath": "params_shard_253.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": "c29361b41e2ebcb12efe661e205a4b7d" }, { "dataPath": "params_shard_254.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": "3994b8e5143173c645b59ee70997fb7f" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d55d48c89c2ad2c48acd781f6a5c3870" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.44.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "d72e1aa0a0d679e5dd779ed63661acd3" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "484ffdd8a6e367e0299cf99a2d93a911" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5e78453ac4b6898c18a622c44b759c31" }, { "dataPath": "params_shard_259.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": "75f3d0d735fa6b177a15acbc5477792a" }, { "dataPath": "params_shard_260.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": "030b747be4e533042bbb6bbd923eb57b" }, { "dataPath": "params_shard_261.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": "2bcab80668ba1a2680749ca5f08e6167" }, { "dataPath": "params_shard_262.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": "e07fd9a67e88de79539cbee359d65842" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.45.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.46.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "6825697de8400da0f51c58e520969b64" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f540b7ed798ad0433f8fc3221ae7adda" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "32cc852243db0bb985446480358d4b31" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "485cb9deff9f73c36d8c521e01cc2421" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b59cbc5e2dd990c1c6d51910e8fab254" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "9369cf402547097bafe92be280517c4f" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "62fc622c609d8c2875197629015bd43b" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "134229812dc8ea59c598fe9db04bcbdf" }, { "dataPath": "params_shard_271.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": "3908d57710dcbcb8c65b2fc08ef0cd6d" }, { "dataPath": "params_shard_272.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": "c14bbfcee11c9147278353f1ed173722" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6bec7f4c8a66390eee95284fb820c9c2" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.47.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "dd06d714306ae73943a08091009702ca" }, { "dataPath": "params_shard_275.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "612d308bea33830d2acacc941447fe11" }, { "dataPath": "params_shard_276.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c40b0520d08cfbf60c178542c410d747" }, { "dataPath": "params_shard_277.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.48.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "48d8ab593a0ec51662ad942b2675f47c" }, { "dataPath": "params_shard_278.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f18725212549016f8960d8d0158e16ea" }, { "dataPath": "params_shard_279.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.49.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "dc26acb7fb969faf35970f3846892ab9" }, { "dataPath": "params_shard_280.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3bb11375a144cd597b9437ac51d5edb4" }, { "dataPath": "params_shard_281.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.48.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.49.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "b98c61e93551e3933c1dba255d831e0d" }, { "dataPath": "params_shard_282.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "0a5f95d7065847e32578d10133d7a6e2" }, { "dataPath": "params_shard_283.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "bd7b8d940d6ee79e66a9195e02466a0d" }, { "dataPath": "params_shard_284.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "38b3811d75ba982f09c0f75e9e352228" }, { "dataPath": "params_shard_285.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "09747ed83783093e0d21bafae8784031" }, { "dataPath": "params_shard_286.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "630e0ba02288ba4a1b21158dc63be0d1" }, { "dataPath": "params_shard_287.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "813880a78241f4a69189d366860b8fa3" }, { "dataPath": "params_shard_288.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "d1945190595900514d297e77e46dc967" }, { "dataPath": "params_shard_289.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.50.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e796681bfa604ff8ac4b482205602b17" }, { "dataPath": "params_shard_290.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "16e6fa48a172a339e8be4df9ad057cbe" }, { "dataPath": "params_shard_291.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "32dd2309fd911c539b38165ad36e8193" }, { "dataPath": "params_shard_292.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.50.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "2f741d266ebfc3d9bd63d7c79a88b9fa" }, { "dataPath": "params_shard_293.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "513f1706b41a396a3bf00f5fad8b7029" }, { "dataPath": "params_shard_294.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "1d23a0a73c4dceb397b200eedfdf9287" }, { "dataPath": "params_shard_295.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.51.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0a8874458a3dc4172637e6ff96a8f285" }, { "dataPath": "params_shard_296.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9559b57650af15dc14d5ca78edfa009f" }, { "dataPath": "params_shard_297.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "fcb3f4654a9819d1067b81aab811cc49" }, { "dataPath": "params_shard_298.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.51.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "ca4fd120f81a490bd389a7492f8c4ead" }, { "dataPath": "params_shard_299.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f411563f96db2a2777678b2b079bcb05" }, { "dataPath": "params_shard_300.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "01a6e3cb09e84cd453ff99e5d49685ed" }, { "dataPath": "params_shard_301.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.52.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "50d663b302c1f8daa300355097149106" }, { "dataPath": "params_shard_302.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "cbe37b25b133c8d536f87a7797256ceb" }, { "dataPath": "params_shard_303.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "dc2352b91b3ecc0685259beb753cb870" }, { "dataPath": "params_shard_304.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.52.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "78497c851caa6599b3d40d13dfbc76db" }, { "dataPath": "params_shard_305.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "66432f11562d5c5949f2a8cfdf290b65" }, { "dataPath": "params_shard_306.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "07e264f07db20eecd2b5099c76c7ffb0" }, { "dataPath": "params_shard_307.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.53.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5c0e6bc59c33b760790e6fc8a8f11b67" }, { "dataPath": "params_shard_308.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "53b8164a33b080254f7a2626a4cdf534" }, { "dataPath": "params_shard_309.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "12aeacde69bf6ca6cca041d137659e7f" }, { "dataPath": "params_shard_310.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "d72d78f33629d3af30eebfe4336e4ce8" }, { "dataPath": "params_shard_311.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.54.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2818532139a0a32eb6ced01db1f76c32" }, { "dataPath": "params_shard_312.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "93f357bd6956c6cb788f4bc1f0ba09b5" }, { "dataPath": "params_shard_313.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.53.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.54.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "812177f5fe51b74c4f4b87b1bcd434c3" }, { "dataPath": "params_shard_314.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f5814392b91341b332e26aa632f7b159" }, { "dataPath": "params_shard_315.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4613eec841d47fe1da671af1d3aea006" }, { "dataPath": "params_shard_316.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "3028a9204f19dac2059ddaf6c65f3dcc" }, { "dataPath": "params_shard_317.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6dc8aba0a90d6bbbc604a1e9198f17fa" }, { "dataPath": "params_shard_318.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3f2d7774ff00fcfb3cf7f9c96f38a3fd" }, { "dataPath": "params_shard_319.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.55.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "03e17065679c7a7e87f716cd53c52dbf" }, { "dataPath": "params_shard_320.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c39a8b6fdfc1d2ed9e8b109e4dcdc690" }, { "dataPath": "params_shard_321.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2250fb592255cecf3468881228b520a1" }, { "dataPath": "params_shard_322.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.55.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "e37cb0afd5c1ac4dd09faaf556e9b800" }, { "dataPath": "params_shard_323.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e2a9734fd04cdd0920f74fad848af8d7" }, { "dataPath": "params_shard_324.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a62c36a9467280cd58a56bc1437f80c2" }, { "dataPath": "params_shard_325.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.56.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d054e280d65b5d5539d510838ff5fc7e" }, { "dataPath": "params_shard_326.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f5d030d3fe168ace9f69c99ed539d158" }, { "dataPath": "params_shard_327.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "15e588b743ea3feb363d53a6569386b5" }, { "dataPath": "params_shard_328.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9fa119406f131f2ec4a2fef13453f3e2" }, { "dataPath": "params_shard_329.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.57.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "996e5b344c2ecb2c2464141106f7d3b2" }, { "dataPath": "params_shard_330.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "77621618de9eb06190bd0e8822bc874f" }, { "dataPath": "params_shard_331.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.56.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.57.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "f7aff98ed4c36143bcafcc832d416b07" }, { "dataPath": "params_shard_332.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d5ad87ed06fe42170112a21f888ced7b" }, { "dataPath": "params_shard_333.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2534880021f12296e0ac1bdce8fb7ace" }, { "dataPath": "params_shard_334.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "d6384e89e55d463fafc85c73c5555ce7" }, { "dataPath": "params_shard_335.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6a344e4b72423f1ca2e3dbfeb617e0ee" }, { "dataPath": "params_shard_336.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "fa75ed3b5268040a3968681796ebe7fe" }, { "dataPath": "params_shard_337.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.58.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a710ed6d616b70bab45a4d4d2f0b8858" }, { "dataPath": "params_shard_338.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "be5cd1c680243a5bc9bf149f3d49ac55" }, { "dataPath": "params_shard_339.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "acb2c5b13f1152ebaeb65d8421152598" }, { "dataPath": "params_shard_340.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.58.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "38528de8d257278920266549d574c538" }, { "dataPath": "params_shard_341.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9d092418250ff6ba0967be48aa90d894" }, { "dataPath": "params_shard_342.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5784bb42c68488ae642712d04440aae9" }, { "dataPath": "params_shard_343.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.59.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5cfcceea4b4ffa7ac54e0589df516444" }, { "dataPath": "params_shard_344.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3a5b45db7f047fa3f4a2df3f6b33fa12" }, { "dataPath": "params_shard_345.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.60.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b8b395d98e2ef5365bec7bc7cfef1612" }, { "dataPath": "params_shard_346.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e2224fe1a4c433b74fcd4dd4ce0b643d" }, { "dataPath": "params_shard_347.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.59.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.60.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "a877a11e690d611db7e809ccc010df16" }, { "dataPath": "params_shard_348.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6ebf3d60704a5b62e7eaf47003ac4425" }, { "dataPath": "params_shard_349.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e314fd6d72f7f7775f719b9cbbeab54e" }, { "dataPath": "params_shard_350.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ef33db5e4fad4153a590c34613668878" }, { "dataPath": "params_shard_351.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "69d46f887596bf8a405d1931e24746dc" }, { "dataPath": "params_shard_352.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "60800eb98d00e10336b56bd79d3507ad" }, { "dataPath": "params_shard_353.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a5095532702ce08488d03b3c875f52c3" }, { "dataPath": "params_shard_354.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8f25fe64665c4db87ce1b160ad2510dc" }, { "dataPath": "params_shard_355.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.61.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c0175d43d36ca215fb428151815177bc" }, { "dataPath": "params_shard_356.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4ca76dc211ebf1049014ced630154795" }, { "dataPath": "params_shard_357.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9c7b3baed3d989508be8bb688d4f8b25" }, { "dataPath": "params_shard_358.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.61.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "f35827083ddd77fca38cae7c05a80b7f" }, { "dataPath": "params_shard_359.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "97cf1f08a98a192e673389133d97565b" }, { "dataPath": "params_shard_360.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "80eee7d649ee5ec253a15db9ff03c87a" }, { "dataPath": "params_shard_361.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.62.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0687a23e5df755f5fae4b4bf0d33e651" }, { "dataPath": "params_shard_362.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5a33463dae4791ba7cf6e24846656fcb" }, { "dataPath": "params_shard_363.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.63.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4e4aeb9f8937f8652b90ec5da3248a4d" }, { "dataPath": "params_shard_364.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c013b120f5e03c774996421b35fd8fe3" }, { "dataPath": "params_shard_365.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.62.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.63.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "9cb4b94b2bfe02b77f43d63a015cbc7d" }, { "dataPath": "params_shard_366.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "fc52ef1fc43899284235fc835d11b2f5" }, { "dataPath": "params_shard_367.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "cfdb6b7f29f35a72908576a0deea51bf" }, { "dataPath": "params_shard_368.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2d6f26701aa0bd64a4f469c67adddd91" }, { "dataPath": "params_shard_369.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.64.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6e6cf74a8750b69c9438a70b28b4c5c6" }, { "dataPath": "params_shard_370.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.64.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "e77231e1d7a63dbd0c283e0e299d7cee" }, { "dataPath": "params_shard_371.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "8cfacee7717f20c9f210a6940f131ece" }, { "dataPath": "params_shard_372.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4b1208c699d577b291b321a18340bfb7" }, { "dataPath": "params_shard_373.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.64.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6c7e0484293eaf1709f3acff23e889b8" }, { "dataPath": "params_shard_374.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.64.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a272d67faa02f1e776d2bcbd44431f99" }, { "dataPath": "params_shard_375.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.65.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "29af1b7176571bdf9e8fadaedd00c6ce" }, { "dataPath": "params_shard_376.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.64.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.64.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.64.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.64.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.65.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "9dee4c49994a5b06a3f83f675231ad3c" }, { "dataPath": "params_shard_377.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "fc08de8a7188f6662d23178073b4c292" }, { "dataPath": "params_shard_378.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9fd09dfa0374ae71ffe9827670be22de" }, { "dataPath": "params_shard_379.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.65.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6ae50bd5c16a558d67340b93fe1d0455" }, { "dataPath": "params_shard_380.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.65.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5077c4933ea3a8bec32683a2a06f6a7e" }, { "dataPath": "params_shard_381.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.66.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e2c7b28f3fb763f539eb433a4f6c4866" }, { "dataPath": "params_shard_382.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.65.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.65.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.65.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.65.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.66.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "fd57e595485f0d0c92f88d848795ecc6" }, { "dataPath": "params_shard_383.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "fcfaee9b58d78af675c7574aaa24adbc" }, { "dataPath": "params_shard_384.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "cf49bbd579662942ca83a4950d98279d" }, { "dataPath": "params_shard_385.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.66.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0415366845b8abb6a0e7497f1f37e1af" }, { "dataPath": "params_shard_386.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.66.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2badec1e6ff026f087d64aae76dc8a7f" }, { "dataPath": "params_shard_387.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.67.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ad921ffff4c57ca5abf903c9e8b31368" }, { "dataPath": "params_shard_388.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.66.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.66.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.66.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.66.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.67.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "31b2278b6ef2d7a888530924a8ba80af" }, { "dataPath": "params_shard_389.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f7562073e5efc295cde7e7c4dc34ff76" }, { "dataPath": "params_shard_390.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "fa8f9eeb77551074879128836716d5a2" }, { "dataPath": "params_shard_391.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.67.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6a1faf6117c008f458143d345877bc21" }, { "dataPath": "params_shard_392.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.67.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6faea48295a92ec521de351560cb9812" }, { "dataPath": "params_shard_393.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b35c16726ab4146eaab988bdf183baf4" }, { "dataPath": "params_shard_394.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ec11dc2bd846c555cc4d9911b10b6d56" }, { "dataPath": "params_shard_395.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.68.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "60b88a5b63f63d4840f97fa96a541863" }, { "dataPath": "params_shard_396.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "178797fc6ec1c2b7eb3ab038e867e042" }, { "dataPath": "params_shard_397.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.67.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.67.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.67.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.67.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.68.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "1a86057eb788ffb69a7b58645ce31975" }, { "dataPath": "params_shard_398.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.68.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6140320058499a5dabe2a604f2a7afbc" }, { "dataPath": "params_shard_399.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.69.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "cc4b1053b00a4c90a44c5c5d60b7ac1e" }, { "dataPath": "params_shard_400.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.68.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.68.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.68.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.69.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "4a5987ff6c33d42911644eac4be95914" }, { "dataPath": "params_shard_401.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5d4b986df9178d1720b213f2754bc3c2" }, { "dataPath": "params_shard_402.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a72f8a5c8cc98120f402bceef6c4f611" }, { "dataPath": "params_shard_403.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.69.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d46ed7381873555826f8af85c3eaacc6" }, { "dataPath": "params_shard_404.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.69.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "92a51d8a2a6f393c5e436678effd5ac4" }, { "dataPath": "params_shard_405.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.70.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2f46dad5d10053363c175a0dc743788c" }, { "dataPath": "params_shard_406.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.69.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.69.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.69.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.69.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.70.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "31012690a77c2cf6a123da8e241a4487" }, { "dataPath": "params_shard_407.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7bbec664bdba7a60f20ce603b22e9ee3" }, { "dataPath": "params_shard_408.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "cf0147e7d363a4c301ba083c51f8498d" }, { "dataPath": "params_shard_409.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.70.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3651418f3692dd78802c30d3bac7cb0c" }, { "dataPath": "params_shard_410.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.70.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "03809809491d447579a19c695e2e4055" }, { "dataPath": "params_shard_411.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bda154c10f3b5b764bbe7678210320c4" }, { "dataPath": "params_shard_412.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "919dfe3b876c70860aa8a60b829ffa91" }, { "dataPath": "params_shard_413.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.71.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4a1ec0876a8c259997d65e661caf2150" }, { "dataPath": "params_shard_414.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3105347278772517a5242b921f64105b" }, { "dataPath": "params_shard_415.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.70.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.70.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.70.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.70.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.71.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "4b9e55565312190d000559aa4cecb405" }, { "dataPath": "params_shard_416.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "23ab1840d6bfca5000426bc5ad2f32bb" }, { "dataPath": "params_shard_417.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d61abe6d5bb58bfb86253d5bbec1f170" }, { "dataPath": "params_shard_418.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b5ab141f4fa20964c2333483bed10677" }, { "dataPath": "params_shard_419.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": "d44c08bb284f78702581c8ee0ead177e" }, { "dataPath": "params_shard_420.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f9793cddff1a3159a8d5d7d35131efcf" }, { "dataPath": "params_shard_421.bin", "format": "raw-shard", "nbytes": 23117824, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 18907136 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 } ], "md5sum": "f5accdf618ad71b1594ac010d48ddc73" }, { "dataPath": "params_shard_422.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "40ab05b40cd28de7ddef67780e1d3532" }, { "dataPath": "params_shard_423.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ed607969095f9a094b881a063f6a4aea" }, { "dataPath": "params_shard_424.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": "475f1abc3d6122568620badefba7d0e3" }, { "dataPath": "params_shard_425.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": "703a5cad77426d7871d5eda29fd19d18" }, { "dataPath": "params_shard_426.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "533a183a6463248df786086dea3642d3" }, { "dataPath": "params_shard_427.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "5721e119156526370b5af7001bfcadb2" }, { "dataPath": "params_shard_428.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "58a9157ef37373093b81c48a7d76b9a7" }, { "dataPath": "params_shard_429.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "437f582265cb2e2e36468cc598ea5c36" }, { "dataPath": "params_shard_430.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": "1f10e8ca8a656ffc23d36b42574704f4" }, { "dataPath": "params_shard_431.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": "34a9c4ee49a3dce0dcce1c3307bcea2f" }, { "dataPath": "params_shard_432.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.71.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "32a307533d46eda999c27b3e6fb3f554" }, { "dataPath": "params_shard_433.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.71.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "ec163c777a536db1ebea878ba7f574ac" }, { "dataPath": "params_shard_434.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.72.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "602c328163d1aa93fa3d4067041acbec" }, { "dataPath": "params_shard_435.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5c9dc37c31d94971ca1f7d4a11012979" }, { "dataPath": "params_shard_436.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "d335c50cbfa7393cbb0bdc296c5a2d15" }, { "dataPath": "params_shard_437.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.72.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "58cddc5eb10df28cd8291c75bdc725d2" }, { "dataPath": "params_shard_438.bin", "format": "raw-shard", "nbytes": 29409280, "records": [ { "name": "model.layers.71.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.71.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.72.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14696448 }, { "name": "model.layers.72.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 14712832 }, { "name": "model.layers.72.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29392896 } ], "md5sum": "4e554ad7717bb0eef6da5f990d03ae7c" }, { "dataPath": "params_shard_439.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.72.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b3df8309450717f316ad17eedd1e9ba0" }, { "dataPath": "params_shard_440.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.73.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "a6a2ccc472da2c03cdff72c6f29e0b0d" }, { "dataPath": "params_shard_441.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "00ae088c8c92e1666e97a698137a9036" }, { "dataPath": "params_shard_442.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "616899c26d69db6367bc995e55b3091c" }, { "dataPath": "params_shard_443.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.73.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7e32e1bbbfdba3cd2801779fd51bc7fe" }, { "dataPath": "params_shard_444.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.73.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e8e0235cfd44299cbca5b8a7296ab563" }, { "dataPath": "params_shard_445.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.72.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.72.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.73.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.73.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 9453568 }, { "name": "model.layers.73.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 }, { "name": "model.layers.73.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24150016 } ], "md5sum": "ea0757caaa72b004a01fd3cc3f78f427" }, { "dataPath": "params_shard_446.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.74.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "52fcf3f7ff11c693c65562ebc1261a37" }, { "dataPath": "params_shard_447.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.74.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6bc14405f3f765c65d01b7387359a41f" }, { "dataPath": "params_shard_448.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.74.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0ca3100d1d580291d69d39c7777c3eaf" }, { "dataPath": "params_shard_449.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9cf640105398b0ff78ac75d0adebf349" }, { "dataPath": "params_shard_450.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "cd0c6da68dc593f34cb68cf0eeecfe13" }, { "dataPath": "params_shard_451.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.75.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "1c32b69574803a4caa3b9a23f68755c8" }, { "dataPath": "params_shard_452.bin", "format": "raw-shard", "nbytes": 28360704, "records": [ { "name": "model.layers.73.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.74.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 4194304 }, { "name": "model.layers.74.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 9437184 }, { "name": "model.layers.74.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13631488 }, { "name": "model.layers.74.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 13647872 }, { "name": "model.layers.74.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28327936 }, { "name": "model.layers.75.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28344320 } ], "md5sum": "be65c977f135a3f3caa6e7fd30967234" }, { "dataPath": "params_shard_453.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d813ae28afb49e8c4d23cc8684abf65a" }, { "dataPath": "params_shard_454.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5b2dca70b38ad5ea7cdeab2fdf04943a" }, { "dataPath": "params_shard_455.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.75.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "52f81e75d85cf03b83f5bff3c5e9674c" }, { "dataPath": "params_shard_456.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.75.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4513310339006bb26b5e8963ddf94a51" }, { "dataPath": "params_shard_457.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.76.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "197ddcba4be804e4a2994f9ac9814a50" }, { "dataPath": "params_shard_458.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.75.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.75.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.75.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.75.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.76.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "2761322de58ab2948dd8bde58c4a07ea" }, { "dataPath": "params_shard_459.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "3aad17227408cee2a0991d2a82f8dcc7" }, { "dataPath": "params_shard_460.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b1215a7f45be8ae59b13e8e6c3a63394" }, { "dataPath": "params_shard_461.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.76.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5b49d51fc7c917670890fe8b40e90b74" }, { "dataPath": "params_shard_462.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.76.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b147c59bba0ab00ca3abed2b91c7b834" }, { "dataPath": "params_shard_463.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.77.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1a64f1a0ab6431373c74967deaa598c7" }, { "dataPath": "params_shard_464.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.77.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "743470c6725473509c00fc8f65004e18" }, { "dataPath": "params_shard_465.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.76.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.76.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.76.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.76.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.77.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.77.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "ebed01ffdf40d75273b27bb785a3ca1b" }, { "dataPath": "params_shard_466.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "47ec3d773eafe878cb0b4da994f12005" }, { "dataPath": "params_shard_467.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2db1c5e77a08592ae81a932dbf80a632" }, { "dataPath": "params_shard_468.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.77.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "566ee6fe0f671b5210206765b87c9a58" }, { "dataPath": "params_shard_469.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.78.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "49ab96471bfaf3e2f4209682034e1c91" }, { "dataPath": "params_shard_470.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.77.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.77.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.77.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.78.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "63bb03b15d6bbca4ea11064b68dbb165" }, { "dataPath": "params_shard_471.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f33e70d8bb6bad31c1c98f8de72447ad" }, { "dataPath": "params_shard_472.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ecfdd5fe19bff7ee1ec8707daf88cdfa" }, { "dataPath": "params_shard_473.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.78.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "f3bdaff18b890904e1d2d09786ebf057" }, { "dataPath": "params_shard_474.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.78.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "594f4f9c85a09c178d48ab97d733ae72" }, { "dataPath": "params_shard_475.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.79.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "665a175b1b8f3662edd9236375f0b674" }, { "dataPath": "params_shard_476.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.78.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.78.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.78.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.78.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.79.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "935e986e4ce36b6a5657419d41f798e0" }, { "dataPath": "params_shard_477.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "84247feb78e49c15fb975be222a314ce" }, { "dataPath": "params_shard_478.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f7b3cedef17f6c3691cb319fa86faf56" }, { "dataPath": "params_shard_479.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.79.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d6d839648d41468eebb3f491d6dd9e4f" }, { "dataPath": "params_shard_480.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.79.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "66b2e53936ef7986e2b20978acc1f5f3" }, { "dataPath": "params_shard_481.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.79.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.79.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.79.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.79.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.norm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "a909ee7ac3e273bc6e38ecaad3b4e382" } ] }