{ "metadata": { "ParamSize": 339, "ParamBytes": 967693952.0, "BitsPerParam": 4.5008284143441 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 155309056, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151669, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 155309056, "byteOffset": 0 } ], "md5sum": "b3d2357fb5890978efd23b64441fa753" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 26495616, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151669, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 19413632, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19413632 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 19417728 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 25709184 } ], "md5sum": "2da7f485772b1c1a86fe8b9ec53f550a" }, { "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": "1ad5320833d2712c2249866704d645ea" }, { "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": "d3d8dff03b27d2ef3862e76a6bdd42c0" }, { "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": "1f24a131072f562ef8b1f16bdf21bd43" }, { "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": "0d20d323070e170565dae2a495e8a6be" }, { "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": "ecd423abb2fdbdafffa8ba6762e6e44c" }, { "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": "ff109475e18a855c621f9bd2cf77832e" }, { "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": "d11dac54ae170c168383c2d742ca4f86" }, { "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": "020ffdd828b9ce57e1fc95b7f049604f" }, { "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": "c60090d2da4dfbf7b6f1a6d41ac3df78" }, { "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": "263c7f47746b2c05af22f1334a97a582" }, { "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": "abdd54dea49217fc7e917f9807cb62bc" }, { "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": "d64a61ca41ca1001231ec60e12de65fb" }, { "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": "c506637a4ed99522233e8b6785955130" }, { "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": "d229bc3bd1a61f3accf0585ce5fd1e83" }, { "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": "8f505526ed475b36db6847f4ef5a82cc" }, { "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": "4aab50884b39b979c15c6d370f135045" }, { "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": "cc63379e61ed0e6c00d73c1be7154140" }, { "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": "2a4ed159f6cf97128b15e24fc770560d" }, { "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": "dd05da15320a33540688d53c28c60bcf" }, { "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": "02f16965839778b1909ead768694a2b9" }, { "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": "f4538ae711f8cb4898fe30422ca698d8" }, { "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": "4451d1b168853cc5f3adb2f5a42584df" }, { "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": "2be62d90e4c732c36731e82ee3cab4de" }, { "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": "85809df9967af9fc0fcda33eefff502b" }, { "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": "5d241a73094cbfc555d58c6c0bbed0da" }, { "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": "fb60edd05bbb02113279e8e47a9f600f" }, { "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": "8baf8222096a95b310422d9e9ef04cce" }, { "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": "dc1389a0e879e31800becc5f24128740" } ] }