{ "metadata": { "ParamSize": 869, "ParamBytes": 2595488384.0, "BitsPerParam": 5.12927057608146 }, "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": "a2730de6700a8da8f261d118b62f7c2f" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.18.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "2d87f603cbd40cc1e02107d1c79ac5d5" }, { "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": "model.h.18.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 6156288 }, { "name": "model.h.18.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 6162432 }, { "name": "model.h.18.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 18745344 }, { "name": "model.h.18.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 20318208 }, { "name": "model.h.18.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 23463936 } ], "md5sum": "c0176ceda7639d2f93622aecdb57fd72" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.19.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "0932f259717d20831b3e4b840854078b" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.18.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.18.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.19.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.19.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.19.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.19.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.19.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "35ace1579e08797658ea555f65591325" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.19.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.19.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.19.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.19.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.20.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "dfaf39fc98e1fd3e5fad7f2614dcf10b" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.20.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "184b3ecb41f2ed3bb57167a9c54cdea1" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.20.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.20.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.20.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.20.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.20.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.20.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "ded4529eceb941a62efd5a32055c40fd" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.21.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ce3bafd5a67f525021d8a32f30f3ee23" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.20.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.20.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.21.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.21.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.21.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.21.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.21.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "459ba8a6ddfb193f3e79c12fc7f1deb4" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.21.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.21.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.21.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.21.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.22.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "3042e78776d44704c65ab5323de2ec63" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.22.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "7a7a195a4ecf23cc2422cf9ef7c2f579" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.22.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.22.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.22.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.22.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.22.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.22.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "e4f69336435b2967ea7a3d362efb830f" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.23.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a146111ecad96618333340c4e0ad6cb6" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.22.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.22.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.23.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.23.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.23.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.23.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.23.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "f0253df1203b62b0ea34c971e21e7868" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.23.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.23.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.23.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.23.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.24.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "5345493ecb8246c25ec64722798b713e" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.24.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "bcee40ddb87bb0ecf2cc95891dd4d55a" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.24.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.24.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.24.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.24.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.24.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.24.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "d47f29d6588fdbc236db4e9a3cc8c847" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.25.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c621d09ed1d897a45b7108f5bb02d5bd" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.24.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.24.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.25.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.25.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.25.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.25.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.25.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "3d4cee43c30013960013451d2630819e" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.25.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.25.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.25.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.25.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.26.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "bd193921647ae72d91094a30329611ad" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.26.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "808339d416cb56985f4adfec7a0a6509" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.26.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.26.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.26.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.26.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.26.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.26.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "61b2aa6694b1361f7c670d1692e16168" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.27.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c6b006f80c310f314db7b6ebabfe5b23" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.26.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.26.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.27.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.27.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.27.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.27.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.27.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "78d21de072db62ce75903a9d77761383" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.27.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.27.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.27.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.27.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.28.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "2d377c0a2b288b3e64b2226f24bc4baa" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.28.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "6f4702d5229c84b5f5f020b2236daec4" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.28.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.28.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.28.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.28.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.28.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.28.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "ecf846c8c16d60521f8d6c05be38dceb" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.29.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "872c8b2d35317e8b9887bce5e1e2e509" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.28.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.28.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.29.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.29.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.29.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.29.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.29.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "1190b419bed563a81feda602c062fb9c" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.29.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.29.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.29.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.29.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.30.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "add1825fb7e3ac0441669ac726c095f4" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.30.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "9dcba5947f6e4d834dbbfbe48fcd6a88" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.30.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.30.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.30.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.30.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.30.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.30.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "3bbd98737ceab5a2d91da88254e99e7f" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.31.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "115d3216c992ec286bb0b7ebc6764d75" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.30.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.30.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.31.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.31.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.31.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.31.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.31.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "47a4f2967e2fbc44edad8d664fc458fe" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 49250304, "records": [ { "name": "model.embd.q_weight", "shape": [ 32064, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 49250304, "byteOffset": 0 } ], "md5sum": "9473898a683287b15fa20c80820a1a80" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 27402240, "records": [ { "name": "model.h.31.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.31.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.31.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.31.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.norm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 }, { "name": "model.embd.q_scale", "shape": [ 32064, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6156288, "byteOffset": 21239808 }, { "name": "model.h.0.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 27396096 } ], "md5sum": "55b05f12c534a87b3a22c6bbf6fa2329" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.0.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "6ff758d383d7bfc1b57e6bef512334f6" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.0.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.0.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.0.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.0.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.0.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.0.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "2fd0c7547e944b5dccf9e130e14d994e" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.1.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ab1ab2eefb8d5f933d8b7dd1b24471a6" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.0.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.0.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.1.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.1.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.1.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.1.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.1.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "1d2f8e4ffe9a989838f545ef6e12d6fd" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.1.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.1.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.1.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.1.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.10.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "b74341c39bd3ef26350ca53836f8c791" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.10.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "6b84e05237d31409763ee66129e56c38" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.10.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.10.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.10.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.10.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.10.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.10.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "5a823ca7de0f4e52b85080a9e2858ec0" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.11.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "4571c5859b9c1b57bedebb97d538bbc2" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.10.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.10.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.11.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.11.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.11.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.11.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.11.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "6938afd56e1d315d2e18fd298ea24cd3" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.11.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.11.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.11.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.11.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.12.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "0ababb0faa05ac4b075cec0a74238708" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.12.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a952d9d81b1d89d2dd8257012255f5d1" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.12.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.12.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.12.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.12.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.12.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.12.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "813f3c9422c6069eb65133c77f89abce" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.13.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "728ccd85eb8b4760b119e4a47027a67c" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.12.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.12.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.13.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.13.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.13.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.13.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.13.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "784a6ab4d0ea102054bff4b0f9ceb3d1" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.13.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.13.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.13.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.13.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.14.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "1062ae0b66c07a9eca7ee42a96accba8" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.14.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "5048cfa14492fdc8defae0228829ecae" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.14.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.14.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.14.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.14.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.14.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.14.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "f8726cd482de23808b02dbc9a6380d26" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.15.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "f41f72ca893928743b0819556e7bb3c8" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.14.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.14.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.15.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.15.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.15.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.15.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.15.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "c483c46c548edc8f5b178fad748087dd" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.15.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.15.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.15.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.15.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.16.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "8f46057779e5691a9c3fe4888bb9de92" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.16.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d4934aa10009bdabe96f10853da997ab" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.16.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.16.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.16.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.16.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.16.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.16.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "21e5639fda8cb757002d75277ae09404" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.17.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e7788fb5830a85dd6c5cb83c524de0d9" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.16.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.16.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.17.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.17.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.17.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.17.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.17.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "28e9a770d395e47416263647d6fe8b91" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 26548224, "records": [ { "name": "model.h.17.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.17.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.17.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.17.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.18.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 21233664 }, { "name": "model.h.18.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 25952256 }, { "name": "model.h.2.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 26542080 } ], "md5sum": "90c950139fd5235a6f98bc9a2fa1ac34" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.2.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "26e3057f7eaa708047e619e41481aa39" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.2.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.2.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.2.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.2.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.2.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.2.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "3f1ac1713af531ebc445ca98eee8da9b" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.3.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "0a38a45bb17da5cee40180f2f75c53ba" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.2.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.2.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.3.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.3.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.3.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.3.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.3.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "0b9fc2da0688d4960726c06acbe42037" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.3.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.3.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.3.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.3.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.4.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "c142df48619f29c8bf3c525a1b69f607" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.4.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a1937eca44a09ca8d5d119cac0710e45" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.4.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.4.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.4.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.4.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.4.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.4.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "1141250328b11b976141c4d4423998fe" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.5.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ef0eef50809ddac84348f609da645d19" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.4.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.4.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.5.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.5.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.5.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.5.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.5.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "826989af93cbf1aaab6875afe5e9991d" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.5.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.5.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.5.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.5.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.6.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "99266d8e478da4e71804b179fcb6d145" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.6.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e59b9d24aa1e4aef4a1cdc8f4e9a44db" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.6.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.6.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.6.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.6.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.6.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.6.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "0cdd63a4a4bb32b016c0eb6f1a49c63b" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.7.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c675ac04803549857bef472c165e0a77" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.6.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.6.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.7.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.7.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.7.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.7.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.7.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "5efd93ae10b1c6f4b17c9a6b1e7cdb19" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 21239808, "records": [ { "name": "model.h.7.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.7.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.7.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.7.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "model.h.8.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 21233664 } ], "md5sum": "321761153751363bd26c6f8f11e88a0c" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.8.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "80ad2d45d4c3c63ce24e81645d034b74" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 22616064, "records": [ { "name": "model.h.8.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.h.8.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.h.8.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.h.8.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 17301504 }, { "name": "model.h.8.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17307648 }, { "name": "model.h.8.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 22026240 } ], "md5sum": "9afcb2ca0c91eb76fbda757309b88b58" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.h.9.mlp.gate_up_proj.q_weight", "shape": [ 16384, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "77bdf7012687732e5175e9d4b67b7b66" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 33239040, "records": [ { "name": "model.h.8.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.h.8.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 14155776 }, { "name": "model.h.9.ln.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 15925248 }, { "name": "model.h.9.mlp.down_proj.q_weight", "shape": [ 3072, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 15931392 }, { "name": "model.h.9.mlp.down_proj.q_scale", "shape": [ 3072, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1572864, "byteOffset": 28514304 }, { "name": "model.h.9.mlp.gate_up_proj.q_scale", "shape": [ 16384, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 30087168 }, { "name": "model.h.9.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 33232896 } ], "md5sum": "bb69d374b22d4a7437d081eac0def25c" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 32262720, "records": [ { "name": "model.h.9.mixer.out_proj.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 0 }, { "name": "model.h.9.mixer.out_proj.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 4718592 }, { "name": "model.h.9.mixer.qkv_proj.q_weight", "shape": [ 9216, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 5308416 }, { "name": "model.h.9.mixer.qkv_proj.q_scale", "shape": [ 9216, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1769472, "byteOffset": 19464192 }, { "name": "vision_embed_tokens.glb_GN", "shape": [ 1, 1, 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "vision_embed_tokens.img_processor.vision_model.embeddings.class_embedding", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21241856 }, { "name": "vision_embed_tokens.img_processor.vision_model.embeddings.patch_embedding.weight", "shape": [ 1024, 3, 14, 14 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1204224, "byteOffset": 21243904 }, { "name": "vision_embed_tokens.img_processor.vision_model.embeddings.position_embedding.q_weight", "shape": [ 577, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 295424, "byteOffset": 22448128 }, { "name": "vision_embed_tokens.img_processor.vision_model.embeddings.position_embedding.q_scale", "shape": [ 577, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 36928, "byteOffset": 22743552 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 22780480 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 22782528 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 22784576 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 22786624 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 22788672 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22796864 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24894016 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 25156160 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 25158208 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 27255360 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 27517504 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 27519552 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 28043840 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28109376 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 28111424 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 28635712 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28701248 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 28703296 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 29227584 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 29293120 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 29295168 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 29819456 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 29884992 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 29887040 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 29889088 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 29891136 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29893184 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29901376 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 31998528 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 32260672 } ], "md5sum": "71eb5c90f02b519dc17163d065af1427" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 33161216, "records": [ { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 2359296 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 2361344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 2885632 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 2951168 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 2953216 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 3477504 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 3543040 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 3545088 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 4069376 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4134912 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 4136960 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 4661248 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4726784 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4728832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4730880 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4732928 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 4734976 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 4743168 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 6840320 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7102464 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7104512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9201664 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 9463808 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 9465856 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 9990144 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 10055680 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 10057728 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 10582016 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 10647552 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 10649600 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 11173888 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11239424 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 11241472 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 11765760 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11831296 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11833344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11835392 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11837440 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11839488 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 11847680 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 13944832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14206976 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 14209024 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 16306176 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 16568320 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 16570368 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 17094656 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 17160192 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 17162240 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 17686528 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 17752064 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 17754112 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 18278400 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18343936 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18345984 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 18870272 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18935808 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18937856 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18939904 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18941952 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 18944000 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18952192 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 21049344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21311488 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 21313536 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 23410688 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 23672832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 23674880 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 24199168 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 24264704 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 24266752 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 24791040 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 24856576 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 24858624 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 25382912 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 25448448 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25450496 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 25974784 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26040320 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26042368 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26044416 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26046464 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 26048512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26056704 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 28153856 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28416000 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28418048 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30515200 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 30777344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 30779392 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 31303680 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 31369216 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 31371264 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 31895552 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 31961088 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 31963136 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 32487424 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 32552960 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 32555008 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 33079296 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 33144832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 33146880 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 33148928 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 33150976 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33153024 } ], "md5sum": "479e69b8802cd150602526108ff0ec95" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 33140736, "records": [ { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 2359296 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2361344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 4458496 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4720640 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 4722688 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 5246976 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 5312512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 5314560 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 5838848 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 5904384 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 5906432 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 6430720 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 6496256 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 6498304 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 7022592 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7088128 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7090176 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7092224 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7094272 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 7096320 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7104512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9201664 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 9463808 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 9465856 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 11563008 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11825152 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 11827200 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 12351488 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 12417024 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 12419072 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 12943360 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 13008896 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 13010944 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 13535232 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 13600768 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 13602816 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 14127104 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14192640 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14194688 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14196736 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14198784 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 14200832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 14209024 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 16306176 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 16568320 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16570368 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18667520 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18929664 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18931712 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 19456000 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 19521536 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 19523584 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 20047872 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 20113408 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 20115456 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 20639744 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 20705280 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 20707328 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 21231616 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21297152 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21299200 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21301248 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21303296 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 21305344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 21313536 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 23410688 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 23672832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23674880 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 25772032 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26034176 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 26036224 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 26560512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26626048 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 26628096 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 27152384 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 27217920 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 27219968 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 27744256 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 27809792 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 27811840 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 28336128 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28401664 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28403712 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28405760 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28407808 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 28409856 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28418048 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30515200 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 30777344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 30779392 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 32876544 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 33138688 } ], "md5sum": "0d5f74cda6a152ad76b96fff892004bf" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 33161216, "records": [ { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 0 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 524288 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 589824 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 591872 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 1116160 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 1181696 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 1183744 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 1708032 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 1773568 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 1775616 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 2299904 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 2365440 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 2367488 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 2369536 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 2371584 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 2373632 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2381824 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 4478976 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4741120 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 4743168 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 6840320 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7102464 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 7104512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 7628800 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7694336 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 7696384 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 8220672 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 8286208 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 8288256 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 8812544 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 8878080 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 8880128 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 9404416 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 9469952 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 9472000 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 9474048 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 9476096 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 9478144 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 9486336 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 11583488 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11845632 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 11847680 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 13944832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14206976 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 14209024 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 14733312 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14798848 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 14800896 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 15325184 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 15390720 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 15392768 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 15917056 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 15982592 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 15984640 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 16508928 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 16574464 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 16576512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 16578560 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 16580608 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 16582656 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16590848 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18688000 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18950144 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18952192 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 21049344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21311488 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 21313536 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 21837824 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21903360 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 21905408 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 22429696 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 22495232 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 22497280 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 23021568 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 23087104 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 23089152 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 23613440 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 23678976 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 23681024 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 23683072 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 23685120 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 23687168 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23695360 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 25792512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26054656 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26056704 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 28153856 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28416000 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 28418048 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 28942336 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 29007872 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 29009920 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 29534208 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 29599744 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 29601792 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 30126080 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 30191616 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 30193664 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 30717952 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 30783488 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 30785536 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 30787584 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 30789632 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 30791680 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 30799872 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 32897024 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 33159168 } ], "md5sum": "f83684667515df399fab68f06af18213" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 33161216, "records": [ { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 2359296 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 2361344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 2885632 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 2951168 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 2953216 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 3477504 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 3543040 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 3545088 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 4069376 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4134912 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 4136960 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 4661248 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4726784 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4728832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4730880 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4732928 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 4734976 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 4743168 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 6840320 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7102464 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7104512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9201664 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 9463808 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 9465856 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 9990144 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 10055680 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 10057728 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 10582016 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 10647552 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 10649600 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 11173888 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11239424 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 11241472 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 11765760 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11831296 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11833344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11835392 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11837440 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 11839488 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 11847680 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 13944832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14206976 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 14209024 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 16306176 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 16568320 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 16570368 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 17094656 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 17160192 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 17162240 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 17686528 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 17752064 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 17754112 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 18278400 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18343936 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18345984 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 18870272 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18935808 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18937856 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18939904 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18941952 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 18944000 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18952192 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 21049344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21311488 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 21313536 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 23410688 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 23672832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 23674880 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 24199168 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 24264704 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 24266752 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 24791040 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 24856576 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 24858624 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 25382912 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 25448448 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25450496 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 25974784 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26040320 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26042368 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26044416 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26046464 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 26048512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26056704 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 28153856 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28416000 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28418048 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30515200 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 30777344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 30779392 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 31303680 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 31369216 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 31371264 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 31895552 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 31961088 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 31963136 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 32487424 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 32552960 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 32555008 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 33079296 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 33144832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 33146880 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 33148928 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 33150976 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33153024 } ], "md5sum": "e959b0c27c59fabcc0443c6b269f21c5" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 28416000, "records": [ { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 2359296 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2361344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 4458496 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 4720640 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 4722688 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 5246976 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 5312512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 5314560 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 5838848 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 5904384 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 5906432 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 6430720 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 6496256 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 6498304 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 7022592 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7088128 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7090176 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7092224 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 7094272 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 7096320 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7104512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9201664 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 9463808 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 9465856 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 11563008 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 11825152 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 11827200 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 12351488 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 12417024 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 12419072 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 12943360 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 13008896 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 13010944 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 13535232 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 13600768 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 13602816 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 14127104 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14192640 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14194688 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14196736 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 14198784 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 14200832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 14209024 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 16306176 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 16568320 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16570368 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18667520 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 18929664 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 18931712 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 19456000 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 19521536 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 19523584 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 20047872 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 20113408 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 20115456 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 20639744 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 20705280 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 20707328 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 21231616 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm1.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21297152 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm1.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21299200 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21301248 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm2.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 21303296 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 21305344 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc1.q_weight", "shape": [ 4096, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 21313536 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc1.q_scale", "shape": [ 4096, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 23410688 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 23672832 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc2.q_weight", "shape": [ 1024, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23674880 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc2.q_scale", "shape": [ 1024, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 25772032 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26034176 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.k_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 26036224 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.k_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 26560512 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 26626048 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.out_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 26628096 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.out_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 27152384 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 27217920 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.q_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 27219968 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.q_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 27744256 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 27809792 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.v_proj.q_weight", "shape": [ 1024, 128 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 27811840 }, { "name": "vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.v_proj.q_scale", "shape": [ 1024, 32 ], "dtype": "bfloat16", "format": "raw", "nbytes": 65536, "byteOffset": 28336128 }, { "name": "vision_embed_tokens.img_processor.vision_model.post_layernorm.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28401664 }, { "name": "vision_embed_tokens.img_processor.vision_model.post_layernorm.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28403712 }, { "name": "vision_embed_tokens.img_processor.vision_model.pre_layrnorm.bias", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28405760 }, { "name": "vision_embed_tokens.img_processor.vision_model.pre_layrnorm.weight", "shape": [ 1024 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2048, "byteOffset": 28407808 }, { "name": "vision_embed_tokens.img_projection.linear_1.bias", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 28409856 } ], "md5sum": "19070c9325e7d2efe559224ba001ae56" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 12400640, "records": [ { "name": "vision_embed_tokens.img_projection.linear_1.q_weight", "shape": [ 3072, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "vision_embed_tokens.img_projection.linear_1.q_scale", "shape": [ 3072, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "vision_embed_tokens.img_projection.linear_2.bias", "shape": [ 3072 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6144, "byteOffset": 7077888 }, { "name": "vision_embed_tokens.img_projection.linear_2.q_weight", "shape": [ 3072, 384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 7084032 }, { "name": "vision_embed_tokens.img_projection.linear_2.q_scale", "shape": [ 3072, 96 ], "dtype": "bfloat16", "format": "raw", "nbytes": 589824, "byteOffset": 11802624 }, { "name": "vision_embed_tokens.sub_GN", "shape": [ 1, 1, 1, 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 12392448 } ], "md5sum": "0e6cede73fde964dc6681f3ad5f7c16b" } ] }