{ "metadata": { "ParamSize": 437, "ParamBytes": 5120249856.0, "BitsPerParam": 5.001016031849916 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 311164928, "records": [ { "name": "lm_head.q_weight", "shape": [ 151936, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 311164928, "byteOffset": 0 } ], "md5sum": "5b5b8a0a5340728a5831d1de30570910" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 38895616, "records": [ { "name": "lm_head.q_scale", "shape": [ 151936, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 38895616, "byteOffset": 0 } ], "md5sum": "fb713ccebb28ac28037c83a6d2d9cc84" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 311164928, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 311164928, "byteOffset": 0 } ], "md5sum": "469fa950cb00f97c742ac829a692149b" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 38895616, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 38895616, "byteOffset": 0 } ], "md5sum": "387cdf49a61f663f6f11accd4944ead2" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "fc001c467f8119e79edc75dd349a06bf" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 28319744, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 8192 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 25174016 } ], "md5sum": "f1d5fb5cef0592a96fe17af7c9ed3537" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c763c3a2857802b3e5769227587c17c3" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "f3d33c0b1d28b9ffc13859d8671a27c6" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.0.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.0.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "0f83715d6f330cae11024c111b88018e" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b3f198e72b515671c0ef36be802e0b2a" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "bdf832796947b9c238c1d1e84fce9d4f" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.1.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.1.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "c2205133dd89bdc4f4ba52d9afd32524" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d9065b36269db552ab8949f872fe47a9" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "464183d7688eda733c4e7e4c2cce02bc" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.2.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.2.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "6eee7da42e362b579232e27281cb6b11" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1e07f8a719a595b55e57c31f38883e5c" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "af9f9ca30fc2e699e3fc2a2971ece6b6" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.3.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.3.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "1c9d947fe65698624dab38f47bacb7bf" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "bf9cd39fb36266b7d2506c6fc011ebc9" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "3c1dd6933cef15eac118c51232941c9b" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.4.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.4.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "97acc2f1d1bdc13fc95f2da8e0b3938f" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "3c0dac551c028781e9702b908b1a3f0b" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "fb5af6ae5d5a4f8f34da2b41cf7ae7a6" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.5.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.5.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "0752b5df7d305e84930923521fef08a8" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 29893120, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.6.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.6.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 } ], "md5sum": "ca135142e6dff0e8aac26e6637619826" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c1379fd0f97749efa876ad82e8c8d1fb" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "8cf6f1b4823ace3aa8e1837135e15262" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 23609600, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 14155776 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14163968 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 17309696 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23601152 }, { "name": "model.layers.10.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23609344 } ], "md5sum": "45d0fd16ca16374a0357fa060cc795e2" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "78f53dab63766342c4860c47ebf226c7" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "a4797b55a91332c9ca531dd95c3ff59b" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.10.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.11.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "561c9ad9372156f81615a80611dc974e" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b9a7ce9b24a2fc7102d9eaea9d9a58bd" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "64b1d1414a7638ed9d515cb3ac81649a" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.11.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.12.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "15a42f98d1e5fa482ffed2671cf64e5b" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b9cf65358a24082123b74d89b486c99e" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "a491d5538e82cb172d5488e41d93f37b" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.12.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.13.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "87b31d4679764851f7f05c144f4799e9" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8691b364835663d9ff5e1959986a7109" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "98665020608b021951f3631adf5026a4" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.13.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.14.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "0531e49ec904ff62bff666486578f8fb" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ff41a04f6972191e95c3694bd52cef2b" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "b459a4214b7df70a040013738fa2c348" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.14.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.15.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "b2d83bab0fc6b2823f47296ebbd5527d" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "9732bb7087b8615d5fea1f39f458991c" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "b1e47a16121d41458b1f02ef9a97cf58" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.15.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.16.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "12ac5a5d9da886c8731d81378c25fe2b" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "296e4e2a11433c7907fe8ab1034f3187" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 29884928, "records": [ { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.16.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 23593216 }, { "name": "model.layers.17.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29884672 } ], "md5sum": "7511db57798f16bae82af0702de8d561" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "52c0f0e1fc25e1ba2389cfdc91eac51e" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "f27809d8e1537964b8ad1e468987e8a8" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.17.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.7.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "4b0b0ef10325f51d8e0ac7e53e946f8c" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "41f3bce3bcfe619253028c5c14bdca1b" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c8296674a131f381965b7a13c6d9d7d4" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.7.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 9437184 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9437440 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 9445632 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 12591360 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 18882816 }, { "name": "model.layers.8.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 18891008 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 18891264 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 31474176 } ], "md5sum": "5948136c4539e1b5712e9ba5c2064855" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "922d7dbcc9d9d316410143a2587f3689" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "fdd6bea641d081e87cee4b086576d5a0" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.8.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 9437184 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9437440 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 9445632 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 12591360 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 18882816 }, { "name": "model.layers.9.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 18891008 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 18891264 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 31474176 } ], "md5sum": "a2b41bebc3ed55d73bf5d432e94272f8" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "99b08cea28a48e2b89b83c832b156762" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "3c60bf473a9524a0e9ad6abc9570503f" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "d1b3c92016f013277932937ba2f666fe" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 22053376, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.9.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 9437184 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9437440 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 9445632 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 12591360 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 12599552 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 12607744 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 15753472 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 22044928 }, { "name": "model.layers.18.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 22053120 } ], "md5sum": "f0ae9396f065a0b6798dc159bddbd6d9" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "f2de8d986d065183323518e3d106ad33" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "4facaa6cc65d52974c8faf444532f2a2" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.18.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.19.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "3484a3ff1b61d1affce8a0535b8f665b" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "394344d412b881be03e43759ea056b07" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "9aa49047d582689d123d984a664f4dfe" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.19.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.20.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "23441a84d7e42416962190cf45383a45" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b32f55cffeee7c84fd157b22dea67a96" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "a215dd3436bef9d2dc5d4daead891a8f" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.20.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.21.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "cd279576fee9c01537922615e8104270" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d3ebc30c8fa6a1a114631bf84c50afdb" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "6e171d7aaf77f1ef79b654c2d5fa3146" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.21.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.22.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "8f22d6ff55621a8ebd31f9b2a3ff4242" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "85b95731a13704bea13861fc8c3c1093" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "51806c17f03ea0ac2e360c207d2b4077" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.22.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.23.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "4e8ff5adc51f161ed1b88f713f622874" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "22e54ba5bc36d5d6e93bfae055103104" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "0dc94e8633abd111beb76a47c5054a8b" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.23.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.24.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "ffeccccc4073a03747b032a2b3ca8ae9" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "5f060484e40afd4c29f7f98c76f7d375" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "6b2715d06291c2055b312a7424f9c30e" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.24.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.25.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "58d76d1e26537521a79834f1aecd1609" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "dfca07c97509c567060e83bf7b61d3f3" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "632fe83a7eba0b60c3813e4de547c132" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.25.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 26747136 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33038592 }, { "name": "model.layers.26.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 33046784 } ], "md5sum": "97d57e69f05bb70d0af76170b4b61c0b" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "914b5f418fd8f4f758abcb22e8e29cf3" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 29884928, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.26.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 23593216 }, { "name": "model.layers.27.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29884672 } ], "md5sum": "d8d0aa68a3c779b0bd101a9edd2ce2fd" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "70ad88dc8fd0e896673088109cf557f8" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a0c4a77da22150a2fcae3409b90ea576" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "312918027318c12fc79d85e77cc9cac1" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 29909248, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.27.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23593216 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 23601408 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 26747136 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 26755328 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 26763520 } ], "md5sum": "d8a5442feb74fb9a99474f6be9b87fa9" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "92a6c3f38844482ae4eeaf8bd17688d3" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "31051748714c2c660f0e07fbec0fbcf1" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.28.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.28.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "48c3c86b9619fcb6c0d3a5bf6e23ed09" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "778da2f084a33a329c412bd1c427f893" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "de097900169ffdde6677ee659e87ddf7" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.29.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.29.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "3f2af73d569bc6d9ee670734571082ee" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b3588e6eb178229b005df18f04503d87" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "35c9c91bd91b4cda58d9c5ede33ff460" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.30.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.30.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "829ae90db7fced5f35930488a74ab553" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "689f4e58fa6b10563df094dc66cbe3b6" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "70496bf35452e655bffa3a67b09f1b77" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.31.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.31.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "c2098ea9a9465c89bb01ec51f26b0410" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "648e68e33359a1989184ed54d4cb9adb" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "7233f3ae4894d1a8effbc2082e33b85d" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.32.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.32.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "b1842e5907c4acfbfee39de79346484d" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "fffda89346459779be34a332d0b06967" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "696ab85e14b8e9e80599853207208585" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.33.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.33.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "8c0351e1b07c67c6f9e961550e850473" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "728173ef52f62ffbbf84eaf2ee5d1bd3" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "267d071353396b31b31ec4aa14aaae08" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.34.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.34.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29901312 } ], "md5sum": "c23604f69759377160145e6ac4eb1b5d" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 29901312, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 6291456 }, { "name": "model.layers.35.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 6299648 }, { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6299904 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18882816 }, { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 20455680 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28844288 }, { "name": "model.layers.35.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 29892864 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893120 } ], "md5sum": "81abfdea63de71e12dac6fd30fee733b" } ] }