{ "metadata": { "ParamSize": 339, "ParamBytes": 968001536.0, "BitsPerParam": 4.500828151065705 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 155582464, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 155582464, "byteOffset": 0 } ], "md5sum": "509d0fd96de21a93b6b6a2c1bdf2abdd" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 26529792, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 19447808, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19447808 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 19451904 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 25743360 } ], "md5sum": "fc8cdb3d4f78baff36ea1778f3f75adb" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.0.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.0.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "e4a79cccdcdf9eb91c1dfcaaa487a5df" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.1.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.1.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "4de9b6ff6c9ab65556c58118cb8e932d" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.10.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.10.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "f50eb14a65828abd556342f912491dd8" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.11.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.11.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "9378b2623d530686e7e0c55cf0e666cc" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.12.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.12.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "4d819f4c9564219dbcff15ddb7c856a7" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.13.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.13.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "a2c824d7768990c570939f76a490bc7e" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.14.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.14.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "b5ff779fc2546e8042274497e928b5bc" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.15.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.15.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "9a33a8eb48f8902eec812131702c04b8" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.16.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.16.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "775db1543779d43893e003dcb23a0f53" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.17.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.17.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "40bce78a59f1955e04f741380c1de71d" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.18.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.18.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "ecfe7fc0b0cf7ad63ab9469c0fe55c27" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.19.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.19.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "b28b315667572a3683e98334ec94d6bc" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.2.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.2.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "3fbe202c1956017f1026665fd3f5ff12" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.20.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.20.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "2af7c291362530eda2caed99bd16fd52" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.21.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.21.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "eb9ea0dd4d5364ff50f7569c9cfd897c" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.22.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.22.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "6942ba54714c6beb61babbf40a8b7c4a" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.23.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.23.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "a5856b47f147e5fd176ee9f66721c32b" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.24.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.24.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "eb0f350b42d3ecdad39f724f88532c7b" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.25.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.25.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "01935ea74ebff66839e357ce04458fc0" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.26.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.26.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "d03b9d2e68185e516215e2c74c3c18b0" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.27.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.27.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "a45a1ab8f28dfdc1597c2c4d5d763467" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.3.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.3.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "407481870a1afd64bcaaebe3fe47a474" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.4.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.4.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "6d78ad6cfb59d9e821ec77ee84de6382" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.5.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.5.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "76722ff47f00165d84e3674efeb6adbb" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.6.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.6.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "b476289dfd72177c785b724502e73cd4" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.7.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.7.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "b8383f6d885bb908ccde2efacb7b6562" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 28320256, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.8.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.8.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 21242368 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27533824 } ], "md5sum": "3ddca7af5215cf67fbe3585eecb50e12" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 21242368, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 12288, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 12288, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14155776 }, { "name": "model.layers.9.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14159872 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 4096, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14160128 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 4096, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18354432 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878720 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20975872 }, { "name": "model.layers.9.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 21238016 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21238272 } ], "md5sum": "64fa80f57cb4d3f3c2f625c5b7857d08" } ] }