{ "metadata": { "ParamSize": 325, "ParamBytes": 2149644288.0, "BitsPerParam": 4.500600961055312 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 49250304, "records": [ { "name": "lm_head.q_weight", "shape": [ 32064, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 49250304, "byteOffset": 0 } ], "md5sum": "5d3ade109e743cd5c15798661e7d8286" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.21.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "cf0b98ca1ab64c87e69e6ce277a78a4f" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 23470080, "records": [ { "name": "lm_head.q_scale", "shape": [ 32064, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6156288, "byteOffset": 0 }, { "name": "transformer.h.21.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 6156288 }, { "name": "transformer.h.21.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6162432 }, { "name": "transformer.h.21.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 18745344 }, { "name": "transformer.h.21.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 20318208 }, { "name": "transformer.h.21.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 23463936 } ], "md5sum": "a75902655ee93e9766936d8d04550495" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.22.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "da0fe360c3674a5a362b62e85a24c309" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.21.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.21.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.22.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.22.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.22.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.22.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.22.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "8fac199e8184137eed2cb8e5f7fdae09" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.22.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.22.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.22.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.22.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.23.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "5be8a29c75e49df424d78474adcf5130" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.23.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "accbf82efed860560629b506992a5150" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.23.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.23.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.23.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.23.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.23.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.23.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "c79a823362fa59b8ba8a372d21fbbb16" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.24.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d622f4e69f58d1c1e3bba255d6ced649" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.23.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.23.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.24.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.24.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.24.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.24.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.24.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "3be4fef521848bbd8155957278e635b7" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.24.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.24.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.24.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.24.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.25.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "2c82c70fbf9b42077b305dd38f10c151" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.25.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a5813d6ddce781f8e30dd073aaccf1cc" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.25.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.25.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.25.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.25.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.25.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.25.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "2409c69973325029e0a92d60a6426aad" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.26.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1c162ae36ccc999439d07794019e4dfb" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.25.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.25.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.26.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.26.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.26.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.26.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.26.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "8736a06b13a522d5ec2942b887736866" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.26.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.26.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.26.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.26.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.27.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "6b806a1f0d7bd0af07c669f28eb07433" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.27.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "71a2c2da37d3a0fb9fd5d8294e2541be" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.27.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.27.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.27.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.27.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.27.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.27.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "e4593cd92a90daa5e24c2dc168cbb813" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.28.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c26725a03fe5e51a3b2211088bbe99b4" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.27.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.27.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.28.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.28.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.28.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.28.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.28.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "1d477ea69dff80dc5ee1e2aa1beec3d1" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.28.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.28.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.28.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.28.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.29.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "6e6ae3fb0b0c09853c836005de268bd0" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.29.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "20d8364bff4e10027313eef51bd786d8" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.29.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.29.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.29.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.29.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.29.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.29.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "b0ac00e6a4ca85c6f5cbce706689b969" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.30.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "568afe800cd6c09cf1242c61ce177a7e" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.29.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.29.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.30.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.30.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.30.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.30.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.30.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "23e7ccadf813b9d1bed99a45150a6017" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.30.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.30.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.30.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.30.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.31.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "6e81c3b6106d5513a24a9f4a05986000" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.31.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "92f4c312f8fad03ce0345f1e577aa2b8" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.31.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.31.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.31.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.31.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.31.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.31.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "a0837c34cd5e805a6f8e404c303eddb0" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 49250304, "records": [ { "name": "transformer.embd.q_weight", "shape": [ 32064, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 49250304, "byteOffset": 0 } ], "md5sum": "3f9a3cb77fdaedfd62e9720fc14e716e" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 22093824, "records": [ { "name": "transformer.h.31.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.31.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.norm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.embd.q_scale", "shape": [ 32064, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6156288, "byteOffset": 15931392 }, { "name": "transformer.h.0.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 22087680 } ], "md5sum": "558cec08fab0ffd5d16bea7d541d1473" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.0.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a71f084f650dd47014779c256ef83b2e" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.0.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.0.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.0.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.0.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.0.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.0.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "ebe39d1fe3e1532dcd2d292374066cd6" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.1.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "22577b54a99d40133b773cae48f9c66f" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.0.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.0.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.1.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.1.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.1.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.1.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.1.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "bf39893ccfa11155fe34da7acd72cda0" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.1.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.1.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.1.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.1.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.10.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "82f15e59782307f4bb18b7a2d5e26e03" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.10.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "dc90625ba3d0c408e8c7521416bc5820" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.10.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.10.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.10.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.10.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.10.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.10.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "9e59e7ae051a93c4d3929a1732ccc8c8" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.11.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "fd47bee468eda1ea1f97fef873d7d4ad" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.10.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.10.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.11.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.11.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.11.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.11.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.11.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "4f4a56cb45d539c77a39e8200094e7cd" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.11.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.11.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.11.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.11.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.12.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "8ff40e1399963b27eb9fcae98cfa3ac7" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.12.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1511667b42325561b7242d3e034183bb" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.12.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.12.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.12.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.12.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.12.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.12.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "42a356759b6ed8dc642bc79d2e03610d" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.13.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1c2fb72892f5670f81aa5c20157ab0e0" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.12.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.12.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.13.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.13.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.13.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.13.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.13.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "5d91872fb54ec1d4bffc42ac675b62c2" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.13.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.13.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.13.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.13.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.14.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "c60fd06b80ee022171f772c9f55ad45e" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.14.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "3323edc16c5201e054e0b31a2fd2d4c9" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.14.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.14.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.14.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.14.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.14.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.14.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "6c9d975975addedc781032edbfe556a1" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.15.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b637b02eb3eeb60cd9d46e45742409aa" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.14.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.14.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.15.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.15.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.15.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.15.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.15.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "7fd49e844f853019340bf9a2a1120b6b" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.15.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.15.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.15.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.15.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.16.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "13e036e33beff7a3f80b3d292b6f01b1" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.16.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "66db99ef24650e3a5c8c522579cd394c" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.16.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.16.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.16.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.16.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.16.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.16.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "e4cf12d9e0e78ff5b6f140ddcb27500b" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.17.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "88c884e8ea04f6ead38fdaf1c4c77ce7" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.16.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.16.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.17.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.17.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.17.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.17.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.17.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "f4680cbc33fcb042b58528c13ec81c22" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.17.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.17.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.17.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.17.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.18.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "a8b503afdc3f504197adcd2839b059c4" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.18.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "3143e48614ae0993b6459e2a09e49ad5" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.18.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.18.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.18.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.18.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.18.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.18.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "ea5aebd3af1991f4e3eb1ed168980620" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.19.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d15790358cb0cb5f43235ec75c46d8a9" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.18.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.18.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.19.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.19.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.19.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.19.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.19.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "e76c5fac8fc906e8ececd4e65e4f96b3" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.19.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.19.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.19.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.19.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.2.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "0a6a70a29a3a7ff6f06103c6abaa6148" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.2.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "602f5aa79ff4df6396c00ee547454d59" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.2.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.2.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.2.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.2.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.2.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.2.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "af63368bbffbb86d4bef402e87218230" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.20.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ca1e13d89832cd489c02d7c086590c68" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.2.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.2.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.20.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.20.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.20.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.20.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.20.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "b82854d09d54c13c7585cf010360e8ed" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 26548224, "records": [ { "name": "transformer.h.20.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.20.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.20.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.20.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.21.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 21233664 }, { "name": "transformer.h.21.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 25952256 }, { "name": "transformer.h.3.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 26542080 } ], "md5sum": "0a6fbcf904080ac028ff6fd1c998ae19" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.3.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "20234012c9ca110b5349792ece70a681" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.3.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.3.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.3.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.3.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.3.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.3.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "37ff917d93e78280efc131c287d4ce7e" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.4.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b037e0fbc951c3844157f6f66f8d309b" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.3.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.3.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.4.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.4.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.4.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.4.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.4.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "fbc09adbd43b86cb8a64645cf0941f01" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.4.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.4.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.4.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.4.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.5.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "853b854d712cbf0b1f3c1fcbae48f73f" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.5.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "0ffe161ad079e0fa7da50deeae20a779" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.5.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.5.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.5.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.5.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.5.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.5.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "cc2f2e77684c4adccf53acc52f6fc85e" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.6.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ba1265575c89a98199f5f6a276372e9f" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.5.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.5.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.6.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.6.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.6.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.6.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.6.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "c9fe53335ac457885cca5ce48f04c547" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.6.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.6.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.6.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.6.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.7.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "abe9e9ec175f3362260915b33d1f101d" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.7.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "0c7486fd26fcf9ecbd9494b4e5194874" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.7.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.7.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.7.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.7.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.7.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.7.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "b468e7b6d44ddff2d6961999798cb5d4" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.8.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "fa155e48e3a812694daa7e36f4fc22eb" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "transformer.h.7.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.7.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.8.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.h.8.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "transformer.h.8.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.8.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.8.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "f11e9ba9dd6bdcef8620b5cc70677ff1" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "transformer.h.8.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "transformer.h.8.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "transformer.h.8.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "transformer.h.8.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.9.ln.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "ead38bd5b4494d3b74ea121032b2a25b" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "transformer.h.9.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "023a0aba1efb96accd81779ed4809939" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "transformer.h.9.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "transformer.h.9.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.9.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.9.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "transformer.h.9.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "transformer.h.9.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "04fb5a82993c9e4aabf0dca2bb5eea81" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 15925248, "records": [ { "name": "transformer.h.9.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "transformer.h.9.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1769472, "byteOffset": 14155776 } ], "md5sum": "69f3d9a6a7e1d307d0284ad2a78a4ad7" } ] }