{ "metadata": { "ParamSize": 303, "ParamBytes": 3101524480.0, "BitsPerParam": 32.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 81920000, "records": [ { "name": "lm_head.weight", "shape": [ 32000, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 81920000, "byteOffset": 0 } ], "md5sum": "6cfdd5b62190a1b7b28efbc637c2f077" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 81920000, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 32000, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 81920000, "byteOffset": 0 } ], "md5sum": "fd76270740cd14c3745a3a7a7db5bf65" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 26291200, "records": [ { "name": "lm_head_scale", "shape": [ 32000 ], "dtype": "bfloat16", "format": "raw", "nbytes": 64000, "byteOffset": 0 }, { "name": "model.layers.0.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 64000 }, { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 66560 }, { "name": "model.layers.0.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13173760 }, { "name": "model.layers.0.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26280960 } ], "md5sum": "50950db9ea74b8067ee765c52c918fd9" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.0.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.0.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.0.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.0.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.0.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.1.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "9001d3f6fe052f193f8a99d6913ff800" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.1.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.1.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.1.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.1.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.1.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.1.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.10.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "25c6314bb687727f916481b245a9b2bc" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.10.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "c15e043fe5a3dbcc58be43af97e07058" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.10.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.10.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.10.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.10.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.10.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.11.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "90962b2f2375a48f2e1f98031e3ee0b6" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.11.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.11.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.11.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.11.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.11.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.11.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.11.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.12.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "359dcbbb4ecbaff84d7b12f3e5d1e996" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.12.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "38fc68e9b61b48e0f4cc38a838a2086e" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.12.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.12.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.12.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.12.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.12.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.13.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "e2cbdd15efe6173b65da26f2249f9f03" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.13.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.13.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.13.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.13.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.13.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.13.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.13.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.14.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "71ecd08fe47c1d93f3f2467f4a2b1cc9" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.14.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "e6f9d12ea410a1d774178bd586f1a2ba" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.14.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.14.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.14.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.14.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.14.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.15.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "ff522d18c10d2b5a5633e56b846bdbe3" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.15.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.15.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.15.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.15.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.15.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.15.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.15.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.16.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "ce832bbebd7db0f6ff835245c50aa506" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.16.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "bc018a573d73dbe5bdfcab8be5c91653" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.16.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.16.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.16.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.16.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.16.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.17.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "5ab5de7f9cb186e4e0d6b6bfa4032300" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.17.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.17.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.17.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.17.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.17.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.17.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.17.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.18.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "29b791cf985297f6d343709fcbff072e" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.18.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "9c69a8350c24bea5f7d5abdda37e9a13" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.18.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.18.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.18.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.18.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.18.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.19.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "8c03b93b6a0e09ce76b4aeef52c8309a" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.19.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.19.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.19.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.19.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.19.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.19.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.19.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.2.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "c542f35c5fcf35b55bfe9b7005aeb982" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.2.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "6be4129392480e1e7e53b110dfec72ce" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.2.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.2.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.2.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.2.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.2.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.20.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "231c90e514a7109ee8cb822a3b58709f" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.20.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.20.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.20.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.20.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.20.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.20.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.20.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.21.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "0ad65d33233391727331f59c5a72e725" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.21.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "4cb8bcc75e8f5a8e7c7fe95210dbdf87" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.21.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.21.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.21.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.21.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.21.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.22.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.22.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "3d16d0d21d5059c28a87f2f281bebd42" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.22.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.22.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.22.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.22.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.22.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.22.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.22.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.23.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "e00ff3190b71fff7850a18d0de98996d" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.23.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.23.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "5fac89d7202cbd53602a88af23700263" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.23.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.23.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.23.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.23.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.23.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.23.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.24.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.24.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "38377e2bca732f892f3bd5fa16e324a4" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.24.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.24.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.24.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.24.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.24.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.24.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.24.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.25.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "4cfaea934b68e63e81b7db1e3fe6df32" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.25.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.25.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "4be91505f1d6e87359374d1ffec9b491" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.25.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.25.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.25.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.25.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.25.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.25.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.26.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.26.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "d1d8e4c041e91ff08e1e2ed7fc352cef" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.26.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.26.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.26.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.26.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.26.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.26.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.26.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.27.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "88a1a22dfc1e7d445e5147ae8164c2a5" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.27.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.27.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "f3b45756dce22abeb5b815973ee53892" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.27.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.27.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.27.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.27.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.27.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.27.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.28.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.28.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "204da56744574ee91dc3921f2b5c4dee" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.28.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.28.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.28.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.28.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.28.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.28.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.28.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.28.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.29.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "ed51566184c64a7ed9679f50ff586b93" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.29.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.29.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.29.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "b12db03042a161d4d8bbf0807e8e18d7" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.29.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.29.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.29.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.29.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.29.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.29.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.3.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "6172ffc7887a175ed12bc31a3016554c" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.3.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.3.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.3.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.3.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.3.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.3.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.4.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "3531464abd9d70b320743b66fac15f96" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.4.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "2436f04433f33e6615dcf3f095b96bb4" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.4.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.4.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.4.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.4.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.4.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.5.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "8eecdc1d799fbc4557ac31bf700bb2ab" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.5.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.5.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.5.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.5.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.5.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.5.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.5.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.6.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "f6ea640f031e7e19555a8c0a4c922720" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.6.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "0fa33cae3218d6512a96121a1a59df32" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.6.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.6.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.6.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.6.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.6.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.7.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "4220a1fbcf2411b2f14c04206b3de9ec" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 33121408, "records": [ { "name": "model.layers.7.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.7.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.7.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.7.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.7.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.7.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.7.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 }, { "name": "model.layers.8.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 33118848 } ], "md5sum": "2adf418cbe889710f478eb9165c40e1c" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 26224640, "records": [ { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13107200 }, { "name": "model.layers.8.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26214400 } ], "md5sum": "65f8abf4e4ecf3adbf4741862a404eef" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 33111168, "records": [ { "name": "model.layers.8.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.8.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.8.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 13117440 }, { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 13120000 }, { "name": "model.layers.8.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 16396800 }, { "name": "model.layers.8.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 16396928 }, { "name": "model.layers.9.attn_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 20001408 }, { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 1280, 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 20003968 } ], "md5sum": "93809dbbb8e90e2e231abeca488f785a" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 33118848, "records": [ { "name": "model.layers.9.mlp.gate_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 13107200 }, { "name": "model.layers.9.mlp.up_proj.weight", "shape": [ 5120, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 13107200, "byteOffset": 13117440 }, { "name": "model.layers.9.mlp.up_scale", "shape": [ 5120 ], "dtype": "bfloat16", "format": "raw", "nbytes": 10240, "byteOffset": 26224640 }, { "name": "model.layers.9.mlp_branch_scale", "shape": [ 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2560, "byteOffset": 26234880 }, { "name": "model.layers.9.self_attn.o_proj.weight", "shape": [ 1280, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3276800, "byteOffset": 26237440 }, { "name": "model.layers.9.self_attn.qk_scale", "shape": [ 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 128, "byteOffset": 29514240 }, { "name": "model.layers.9.self_attn.qkv_proj.weight", "shape": [ 1408, 1280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3604480, "byteOffset": 29514368 } ], "md5sum": "5727538628b79d8ea0d09fbef4a01ba0" } ] }