{ "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": "4e4ec9b621dc1492b262d3614f56d118" }, { "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": "b2bd237989a5db97d20e2a0be17d4da6" }, { "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": "a1e115bfe2b80ab6e68b11d12f94fd9b" }, { "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": "90ea43e058da9f9c57f6a79fc2b8af50" }, { "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": "c29c91896de5627f1359dca38c1e9f17" }, { "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": "471eb222ce52ed9e258800cd7e2e231e" }, { "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": "88fe8450b77347deafb85d9dcf510c0c" }, { "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": "e063889dd0c32e1e0b9843d686c16ad5" }, { "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": "efadd6cd76cb1672baff442ff64574d0" }, { "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": "2ca4505e39f73c109028e2378ae61fa7" }, { "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": "8658db8ef33787612df793bbcaf98fdd" }, { "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": "ef7deac40ce77039cb3ac3a32d7a2a1d" }, { "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": "d0193f35141920745ab4cfadd04cbcf2" }, { "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": "28be2d66e1794f9ed436b8eb312210e4" }, { "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": "550ded1ca584ec02d934aedf5240c015" }, { "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": "d73c6317ba20d33ada3c877236d775be" }, { "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": "3cde9ee669b618d5b89bac74453e5e2a" }, { "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": "0af6d26f1e8ed3bebd75aa4aabd10baa" }, { "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": "f8951e4b715e88a4e7831e97ce61dd1e" }, { "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": "504db39e2b6f466889e6c9dd94fdb426" }, { "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": "50aff09334b51a4640ae1d2ede505d70" }, { "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": "542c9918be9f19543dcb72f389e9c85d" }, { "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": "a6f6323ba586dc840a717427fc8860e7" }, { "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": "6aab49099fd84ae0e6780f412cf32bc1" }, { "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": "0dae965d693c747a0c83c40c8914f9dc" }, { "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": "925f1f620aa1379de3f612895ee2e899" }, { "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": "5f2fe1526706087f7edb0a279394ecb5" }, { "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": "cad4e3c7a0422c975a0bd2615cdca1c3" }, { "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": "1168d0264a82fe8430121c80e2ff2db8" }, { "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": "91c996292750ac3d87b9822824c83c1e" } ] }