{ "metadata": { "ParamSize": 325, "ParamBytes": 2388848640.0, "BitsPerParam": 5.001410952042906 }, "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": "6a807cc1c8c95fddf9dbc8045acf56fe" }, { "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": "3432ded95515f21c831eab1c444bfe84" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 23470080, "records": [ { "name": "lm_head.q_scale", "shape": [ 32064, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6156288, "byteOffset": 0 }, { "name": "transformer.h.21.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18745344 }, { "name": "transformer.h.21.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 20318208 }, { "name": "transformer.h.21.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 23463936 } ], "md5sum": "c402b8e5abbb4a64de5cc12f365e9c23" }, { "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": "05b2f5239e34248a5c65318513889704" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.22.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.22.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.22.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "ae828fb75136579448bcd2fb9f5855d7" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.23.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "d4e6aeb919c5ac1573ef7dabeff126ce" }, { "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": "9b8ce59905697e772361e28bcabdc4e6" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.23.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.23.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "e25919d263c8d6cfcc2aa1d86526b788" }, { "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": "c42d7054b842dab0506b43491684ef4b" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.24.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.24.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.24.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "7425cb24419ae48a59cb8215b0ea9097" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.25.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "c47f859e24290a4283ccad084e975eb6" }, { "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": "e33e9a48d3a3984ed0fe985362f768b3" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.25.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.25.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "beed666610e2a362699a5e48ce9a3121" }, { "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": "dc22257c904364781c394a62fe4c27ec" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.26.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.26.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.26.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "217ac06b74f18fd9dca86e3dc1b4b9a9" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.27.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "0a58f0d24c8aedc2595195ce3f596493" }, { "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": "6a25f7a2b8263db70774652768ede8b4" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.27.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.27.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "ce928df4303a9f2f9e02f425732c7376" }, { "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": "348b665a7a2701884b6aa7af6b87c8ba" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.28.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.28.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.28.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "d368cc895b176d01ebd604878f1118bc" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.29.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "bd7258a0ee1ed04085458542135bb068" }, { "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": "cf9e62655637f0ad79d2a5dfde07409d" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.29.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.29.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "006f18e66c40061421aefa7a9c80633b" }, { "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": "5ec2c35544c214fb07710583517e331c" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.30.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.30.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.30.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "42e86ec97f0c1571da8caed1ea28964b" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.31.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "038b80bd9a7db3feb58f7597bd1d875b" }, { "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": "5166e8b9950381ee18ae5947d6731d2f" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.31.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.31.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "fe808ccfcfb0376d52292fb0c2f58176" }, { "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": "687f64bb6b3162a847dc57e77fba0487" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.norm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "transformer.embd.q_scale", "shape": [ 32064, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6156288, "byteOffset": 15931392 }, { "name": "transformer.h.0.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 22087680 } ], "md5sum": "123e5f2baeb59a6e667fefe1a897f4be" }, { "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": "1c48a1ebae8b59ea1555909eccaf9a59" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.0.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.0.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "f30f9a95564915211a63af2c933d361d" }, { "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": "97d310a0577ac354bebc773dbfa4a86e" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.1.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.1.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.1.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "245947c73f9d07a45d02083063a73490" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.10.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "c9bc1323f723b0a6671e67d99bd7beaf" }, { "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": "d1b6daef812350e60d012979d99274f7" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.10.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.10.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "189ef83523c9df951496e10809340e41" }, { "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": "40a76940857ec7b1b413f8f30727e434" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.11.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.11.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.11.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "91982e630665f7ea41dde93755d76190" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.12.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "581d8616594c115308686b51881330e6" }, { "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": "afc87a9a2230489c9eeecf848ffeab26" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.12.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.12.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "ff19ebf94f60290adb37ad4cfc3f21be" }, { "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": "2d123fbae5c4deba9a8b8babd3075f8f" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.13.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.13.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.13.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "5157743260119b859bd89924ea2aff06" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.14.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "32c6000319783e24c24396e4ed6ea82e" }, { "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": "63fc2be770b7c8e56dd9ce52ea88ee23" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.14.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.14.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "3f14d5d73bdd2884e7f0124eb0332542" }, { "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": "2493831ac7f264c183f192fb2e738c6a" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.15.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.15.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.15.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "a3e7aece10994dc2655b984d2d4a5e17" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.16.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "3b21fff0730e78e71bab10e2da3125dc" }, { "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": "f3470d6c3c3ffea8b40f0e0ff6164d37" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.16.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.16.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "bfb77eff09b18d953eddc932deca1b1b" }, { "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": "169e67c95d4c0ff486880e7331885278" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.17.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.17.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.17.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "c21e49f4724d1b20af0199c7e409fd49" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.18.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "b51257e8706f752a21d3a1810c03dcce" }, { "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": "b9d014b5ea72c86cc7baa175526ad28d" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.18.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.18.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "1bbb9d1b4d840ab6e5d0466521ff57a9" }, { "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": "0967366d9b928b91e29813888b3efd72" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.19.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.19.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.19.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "baeaa14fb42e17ed982329b8737e7fa2" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.2.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "49ec0157aff3422115239ec3cc86bd5d" }, { "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": "44ca6eb70e1ad8785125609165975431" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.2.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.2.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "1aea1a7840cbdefe95c284452920883a" }, { "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": "51c8928b92922efef4aec8054110750e" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.20.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.20.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.20.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "fa2ea55394491726874d5ca7981188ae" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 25952256 }, { "name": "transformer.h.3.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 26542080 } ], "md5sum": "6da3227fe7ab31aec0bb0102750b9b44" }, { "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": "73d804de838fc5f8e6edd6726b7d694d" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.3.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.3.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "b7bfa87b77c232e9c2952150add1e3fe" }, { "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": "4cbfe76e3a7361495e34ecde6b38191d" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.4.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.4.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.4.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "2f76463b0a52ff25be58278c123806ec" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.5.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "3bf2dd7398928f174d97831f5f83338f" }, { "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": "7deb27a6889101cf366ed1e1fb5b7234" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.5.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.5.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "082ef6379cdf2e29700fdbd939004f03" }, { "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": "4d8eaa7564b70911da70fec01652aedc" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.6.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.6.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.6.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "33300dcb0cb5a3647fa93fae07e9bebe" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.7.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "20c402621c0609375371028acedb4b85" }, { "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": "21ea06992566a3092bcb5e1dd122c469" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.7.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.7.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "aa01306c9d90959259827dfc297f0211" }, { "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": "c54d4e641d4d6f59a30f76b11751c8e8" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "transformer.h.8.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "transformer.h.8.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "transformer.h.8.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "d3b3ac79ab6f13fe0b8967e7a0a61223" }, { "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": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "transformer.h.9.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "2ba4867000e0328ae5729aef0e7585b9" }, { "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": "15a7a05b7330f70ec9be000836b869f0" }, { "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": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "transformer.h.9.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "transformer.h.9.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "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": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "968275025dc4ac4ec0b2f55dc3f2d30e" }, { "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": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 } ], "md5sum": "007be00b2ecf4734c6aa0e174b816d1f" } ] }