{ "metadata": { "ParamSize": 885, "ParamBytes": 45448593408.0, "BitsPerParam": 4.619993414045882 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 622854144, "records": [ { "name": "lm_head.q_weight", "shape": [ 152064, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 622854144, "byteOffset": 0 } ], "md5sum": "7249fc0681a32503edd714f7c9cc6b6a" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 77856768, "records": [ { "name": "lm_head.q_scale", "shape": [ 152064, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 77856768, "byteOffset": 0 } ], "md5sum": "55ea69a594b1646e5b462046e249cb9d" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.79.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "94952715286a35afbd3381eda6b65eec" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "b931fab246b0015989350f4dbd75d095" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "c1d5e6b6b49bc9cd3ea10c16cdea4eb7" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 622854144, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 152064, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 622854144, "byteOffset": 0 } ], "md5sum": "f7c415ed0c1c468e23d021a82fa05e92" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 77856768, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 77856768, "byteOffset": 0 } ], "md5sum": "630b5a8d9b86d61ee8eab3955fb18f4a" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "61e56bda788679680085d0657bba25e7" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "85c50bf9c1a1f4cd5af33da3581738f7" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e26e8a9d8acd6d5f7d4d4576193c55ec" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5c5cb74e53ef41ae30b5db032dd7db37" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "72480eac791a1c9d470812944338ce7a" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 24645632, "records": [ { "name": "model.layers.79.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.norm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15155200 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15171584 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15187968 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15208448 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20451328 } ], "md5sum": "67a327fad1d0827512040ca59e138b0f" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "a65e9cd7aa323f053918d83529aea362" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "6e7414a787550114498e9ad323bb5fd8" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "7fdb8b88ac5ea294e37dadb3a80512a7" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "00b8439fe0e0750f68a3f53d94c56f20" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 30330880, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 15155200 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30294016 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 30310400 } ], "md5sum": "5db086346c54267213a71746cca2490e" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "cc8d0e4192280a2f5493d0c54b1a709a" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "54eefcdc55b46c56daefd2423ddfd6ab" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "1d36b9bedfca273c734796cf3ae49638" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "39bccd2ef544e072bf2b42bbfe826d79" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6fedb93f7c1677a74f0e1f51e1caf18f" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1e3fac6259cba19f3e13e61a47d1112e" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 29872128, "records": [ { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 9453568 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24592384 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24608768 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24629248 } ], "md5sum": "c164c62e3ee57c44b83c28c92809decd" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "c7de339964e39fb92a3601c4d46da890" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "587818da55d92c9a43463dbee40e14f1" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "0a6a306102374dbd649b972e9ad26d11" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8217143f65e4592a0fa7acddeded76ae" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2b538f0dac4d145a52554b2d6bde56d9" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "23b99958fa22ef1674c5524cb76053b9" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 28856320, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 4210688 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4227072 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19365888 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 19382272 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 19402752 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 24645632 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 28839936 } ], "md5sum": "5c999a42842e125a2e02e8b1c6897772" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "9b42381b05fc69d5bb0769bc31d21ba6" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "32b3117161288df615c6e113564c4312" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0bcbcb363d0acd148d72fa2838cbb11e" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f6c36a7814b31b2e1d390ebf25ee6049" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "553840517ddfc7584f0eec1bf98365db" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "33d293ce66808d03ac372a1b5262c51e" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "02bd340b8f533adfd4b13f43b3693559" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "88087e17ff70aee37d217c9d00a80566" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "983f659a845812bfcd691b62c1f49013" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "39547d6dde0890272d39cec66a74708e" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 30314496, "records": [ { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 15138816 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 30277632 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 30294016 } ], "md5sum": "faa46ae1efc8e18567a8d28d4448bea8" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8bbdfca004f45414a6b337348c86a039" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "dd6a49c739aea59616c03e7ee538eae1" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "38ffec1d7db8f38f0cc6483d1b2a1c47" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "b7d5fcfe046e4631f3d3df9d7722b1d2" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3ece95d4777702b17528d5278192a646" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a6bb65f5c555d9ee39f668225e462bb1" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 29872128, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 9453568 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24592384 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24608768 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24629248 } ], "md5sum": "77bba80554d5c3e213ade56b843d3271" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a3e0c6adef9e7260a6f9005fab5403ce" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8240aa89fa709d60a8f5055987c18440" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "f86201bbaa36a49ad8c5bdaf3fff6c8e" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "ddb8d69cb9a02f4035642c2d105105c5" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "8140e0816d3ff5bed44dfee5463bf271" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "d4e798668ccedf1a03e27f0734e6d01e" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 28839936, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 4210688 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 4227072 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 4247552 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 9490432 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 13684736 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 28823552 } ], "md5sum": "0b2aa883e7a6adf4cfbd4a0f08faa3b0" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "69ea69092d478799a72e33f5129afc42" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "b144da13874eb902d6195b3dc151a877" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7fdddd9d5965ce80e9d7b77a389fa4ee" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a52df2e780c0454d470effd33cdba3ad" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "e8fb5481ad0bea5fbaac9773f3930879" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "bc260d6babc48b92731993d2ebdef16e" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0dc9ac1370a6952aba07f53c8a7ef634" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f0423858ace1abd2c529bada7f4aed6c" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "c3f5dd8c15c692ceb149b0cf06b067ea" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "2414fa1e3820e0e39d7646e3fbd941b8" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "50f75df947f374d1f4ba343074e99aa2" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "d011e953dfd75f7ea6df9163e931b1a8" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "7f2722371e7dd185f8c4eb5b291dd6a9" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "a1346e9e136307c299683de462bf0e48" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "71afe2a9f93b1c0bf37a885e93731345" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "039e4a38fc1ebf23e9d481f5475cf4b3" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "3670aca7f06f6c54eb8cc7a20ea4de30" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "6c713189740c729e15a66b98e31d0252" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7aaf63964ba6335ed16a5b01214ea99e" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e9ec59bc5fc2571fdd0e067c80307d96" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "6f9759611ad07eb38e1889878c34829d" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "b7995f3899f6a828e82b01627a368c6f" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "762acfd59f9fc5dd65c4bfd9722a4aab" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "c71993bf742f16e68482279272df2643" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "722e0e64d00fc6efa93add6f7f656675" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "181875f32f08de244d001756bea00ef8" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6d6ce4ba25a6217cce0270319ba6d0a4" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c67ac65763f3b24ca95d5b5fd0341bb5" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "15ea841fdf387f13da0eedc8cdabf2ec" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "1ff4e26ac159f1b30e026e587bdd7221" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "8e5e947d4e81478f5afc9f5a3a4029cd" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "3aab5f778a2ca2d15642ae94365f9ace" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0b2890df16c6d99c719543248941cb62" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "666894ad41e7a32c618d56f6aba7a983" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "ed913a2b3b67e3dbe3fe65d007884015" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "fdbc718e8f3693e37f98ce6ead272f5c" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "afdcd09301409d80081074991ab51c83" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "de5cea10914ca260a3caa1f9d0126c81" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "9679b12e6275523635b5d16fd71245c2" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "901b251a1f9b0ce2adb6ef4667da0200" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "688c3f14857f92a6f75c2d757b3b592c" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "bdaeaebf62936aab0a26859c5a520294" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "038d009ebacc5e1952914c817938578e" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "1b4f27818a8d0ef1943267fff809d0c5" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2e53f53aa845b131a41fa388b525b40f" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4916fd08875a41f56586fd9c058b834f" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e0ead593136dac5465e28ae6d6303203" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "75b321a0e754313efe52eb0c32240219" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "d3af25f29753082167f14dd6168fa2f4" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "66dcfef2afd92ab496e2c9c5866bacc9" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "8857be9c45bdb9d3ef0c445aba584234" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "e454d6a5d201a3636a5f08e6fba8eb36" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "195d8f87c5efad9718435bc4bac954a8" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "ea0c49c105ebbbab559d2fe77dec9ccb" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "a7cbc6dc907f94a72510f58a615104cc" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "2e0ab58538bd504866c82f140eb75f50" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d576fe36764eab3987beb616ebfd7d32" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "03840b43b20be3dd594849234fc122d2" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "4acb116e61e69b0e7a092bb049c1c4a7" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "d2dc484e73a6d33115ad7cf34adbd45e" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0b0e4ec362a1717fb4a86b1ca43d42b1" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c44d7dd139fae1a60b3b43b18aa0fb8b" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "53035e0f0de0d38cc7cfac0cd81aceeb" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "1ee56f5eaf0a08c204bc9e17a3f64e39" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "e8e637dc5fefeba940cf24d81804f56a" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "c7b6bc013cc7892e0be7a058fa83891a" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "cdf07e58c679b8e0ef91f543ca91ce87" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "9518e0e8962ebf82e309a8779c89bd86" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0e2d7a173f35ce08360396054ccc48d7" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "48e2a690e3a46507afc7145471c75be6" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "17b17afb114c5dd5aa998b4cd29283bd" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "9b2211d173232ccfb5c55103f8da811e" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "90233683572bd4616885e7752d56cd2e" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5021b7a62e28b9be37959b2a333dfbaa" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "2299fafd85df48ee3fe833a733b7a7ff" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "28a23864348615d32332e51366b5e34f" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "6f0b06d9ea115354505d5dce29b173b1" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "d08588650852d2971c7efce769b03e6e" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "a3a2b02f03dc78e0f5abf907f294f1b8" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "1be5620bbf3f1c50775b2a16d2b63f6f" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0a78c7b6f910fde9e90c184dd7027e0a" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "06b3256662cfbf0b7a55c41d441d9e80" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "2d6b566f5a679b051a7ae62c2dab995b" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.28.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "46335fd3cdd17a642cb512f687cb9965" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "f493b28ee119b97460b530bc29973778" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "5d1d1595ab70e126e49ee74375c2930c" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "345422fabadff9b107e004db5ff6dafb" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5950179dced638cc7f0feb9571ed309b" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "ca1dda93f85cc07f62bce2eb5d7d3573" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.29.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "0e6d64e24f6e1e5f7e1b20a7793c9d2c" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "a689628bcc7a991be51c202e649d7169" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "766f5a97be54d2d3baf4bb93e1e5b0da" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "455ccabf4ecf092a6d94a9bf7cf8f0d0" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d0089fef178f582633a2698da7f97193" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "b6eaa6498a165652324ecc07918bd771" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "81d6c0ba762600f37d4e00225c3f5f6a" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "f5416417a7ed9f61aa3a80183edefc73" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "69605c1ebd8d5719f814b57f8d055429" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "caa7e508371cd2e0e9e2695a620a6192" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2a45ff3cb279af2a44feaa3f9239f7dc" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a0581f423706b9c2412b22852eabd392" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5b8ec42c618a1a1d72e31cb60380dca1" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "9b430a7c4d3b44160d283d72e4efb9ff" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "d99120d861a1927ccf459daae4803ab0" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "5dfa82124c65f34dca9382fef3d4d414" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "896f3f3d451a6af0539d0be4fdc5575c" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "976350af968ffa007b7127ee077eaed0" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "789af26db398d4dbfa377ebde9138c42" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "8820b931a13270e8b3550564c701c0cb" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 28823552, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 }, { "name": "model.layers.30.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 19349504 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 19369984 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 24612864 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 28807168 } ], "md5sum": "a8b6615f8dcb2230e848a903275cc245" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "38c6d36878f8c09780dc0d70139883a4" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "0ce93628b9f3bc3b58c6822cc512107e" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "99fd33507cbe20b817ea94e4a93b6e0b" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dfbdbd38511600668decc7112c4c21d0" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "10019ee8391a7d6ba51d87d52c91c7fb" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "161e9d5a6d776fecd613146d3ef8523d" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.31.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.32.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "8dbd0e39872f8186d25ab71494ae52cd" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "ce5215708e7f51da36848c9e644cc098" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "3ebc5741ced9facead886b0dd4e909ef" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "97c56a12af2a60174598f66e7a2b2dc3" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "9c1c798706ab18e34ebb65c5ad6aa1f7" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "95283b87b4f4a6821bb3eabb310319ef" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "4fd155ef6a1e6fd9690e78766692d22a" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "5d7599d24d2120b8b075ca24f7d9bf62" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ce3b6542958e41d65ea24acd1eb6ac43" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c41bb5c82ff3eedbb8a8290dd3e0c765" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "3dfd6a9f33e9c8c6de7ed14c7956dfbd" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "71b2fd857d01e65c4406e9c9bd06db64" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1834e673c89f2d04001bf9498a78089b" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "46e661be31a75d6dcc693fad9348a122" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.33.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.34.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "351a40e3bb2da00c1f4ad69ce16d5666" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "1fe9d32f43e85904a146f6962bf14a7a" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "fb10dac4b47d27a3d9257b7c0be0c5e8" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "6f698c3a2ca32e7be7993c56ec43aa30" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "3239b9d73f888b9f9c4b0489cd25128a" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "43907d5117dfa88bb3a8cf36b4746182" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "49510e936128aa924fd53cdbd74263bc" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e4e938b004cdc90e74c4bc3bb8377f6c" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "fa67f0cd0e9cf484b76ecb3e5572c745" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "55bf2b7c76b60e8e810506268e731b68" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.36.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "9bf78fee0e8a7378124663de2ffa8b31" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "44c0359a9675a257f8271a449235e4fb" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.35.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.36.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "941301d0a6a1d12a7434546890a6e44e" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "dda281fbccfefcd67ed2eea409de87ed" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "51d5ca783f189336162119da41d8171f" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "c81eef1a4d6a6796be4f14f9db831c5d" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "d9918d2e6016914b2b57ff4672f51cd0" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "d69bcdf671fe438abebe42d6ff027d6e" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.37.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3cf209d202c2d2c7500ed281650a9937" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d14512c20ef52abdd4711fedad130305" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "22169c2014d4f0ce9297434e3a4edf7d" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.37.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "7d1068fb5199f8472fef9116334f1d78" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "c8178e81c191a7a9cbf44577d7a257ae" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "625cf6030b162a1cfe8d144e2d788aeb" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.38.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e5861311fd8aa1758a915f5e89b554f5" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e71deb46b1c9a15c894cd240fbea2fa6" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "8c196a9d29b9a4ddc3b1aeaf6659d09d" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.38.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.38.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "af1a1c4b9aeec610042042572544630c" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "a2aa3894c708fe52b2b17871f257a253" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "26c3126b651662c5d816fd466fa7e5c6" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.39.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4973b8bc2ee1e23853049013b3335b8f" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b2c6ee93522465daedc39045fef0c3f1" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "a1a8b27a9e5f6cabfcfc694d81f31885" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.39.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "c1c181dd2581f6f5cc90f4700b59444e" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "e336442c3169c595942942c321e82224" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "4250921a7165d5adc127e858d3f59397" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.40.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ae2cb6f6f1567bce2f286253f0cadee0" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dfb8f3fabbf3e99b32741814904f7f2a" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.41.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ca3795964dc7283bffa1eb2e8e487301" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e5f74e990c7f01eb4f7b34189e0b1263" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.40.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.40.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.41.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.41.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "273c33306e9176144d5a813378ba21e9" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "a9c09a6a84c3f9c7a65b6f0882501cba" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "38173b3da1d8d4bc39303dfc2e39b79c" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "dd44f6b76a12bfb44d4c837ffa0e5e2e" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "361bd1d0a69cbb3805fe0d3b72f95e5e" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "e49983e7bd063631f46525cdada042d3" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "83f06bfd8d7c36c4d6f6d1b581d7afa9" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "aa808eb62bf6f14f9948104afff4db00" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.42.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cd9bfab086667ceb43142aa4211a51f9" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9104e024d704b468869116e242cd7662" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "3e5ba6288eafadf75cd0cc1d8246c440" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "c866b148d9154be80a551750a8b78148" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.43.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "38f9fffd698710ca8ae2b50a20396143" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bae9914a6656fbd312576e7cc4a02a9d" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.42.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.42.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.43.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.43.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "e69c68d7e6b6ea2353ddb06044d65396" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "c67670ac6f10845e5a2b8a3aa03657e3" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "4f6d8dd7b8bf4a0eaca0eaf0ba07b78b" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "1df84203489c4dd541f5a1197ef764b7" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "f49ab57857e33610e8999e1feb7ceca4" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "eeb5adc52c55c73a3ebb22a45f671672" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.44.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "34132b0f3aee010de073f77f477858f6" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1513b63a3ffee8de48341403fbe1c049" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "6b463274140150a925d853dbbe856c99" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "29acf4e070dcfa5091601d7e92698eb1" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.45.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7d5622dcfaf5a2eaa649b6c09dbf6b85" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "26f28043df20288c6573e0dd675e76d9" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.44.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.44.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.45.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.45.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "71606dc247c058408578027f4cbe4e92" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "0750c74b21d6bf8f3cf37f01834586c2" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "739d8405de421d67795e965032b4b987" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "3fc54ad2df411c9fa1e2e1e3be09ea20" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "8d69b6e05d71ca3490c55d54d7824453" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "b6bd1314831e15454bd7793d1785264f" }, { "dataPath": "params_shard_259.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.46.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "89abf430cf5b34f5ab07544d79b25fb8" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d0b83fb7a46efbd1d5f776c3d44b498a" }, { "dataPath": "params_shard_261.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "befd7fe2a35f9d0de25e113eb404d134" }, { "dataPath": "params_shard_262.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.46.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.46.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "4a5c513d4dfb6d7637288b00c9fb312f" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "43f87df477096067cd22dc5d12cb6f0a" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "948336ce629e39f7842da1466848f2e9" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.47.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "30a67c779e531490e60859d656943e8c" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1ab97c18df66397942ef0bf35f12c181" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "96f2896fe9a62d5542c1c5bdb0cdda5a" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.47.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.47.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "60e0ac0e22528ced716e6a516733a362" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "c75f1d57326e3b78245e7b3e26735624" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "9f25048edfbb8f7be4e32dfc1d5173ef" }, { "dataPath": "params_shard_271.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.48.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "66554c9d34f77770790c1c2d724fab9a" }, { "dataPath": "params_shard_272.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b4646db80e9e0f21a8535ed606f42232" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "a5f25291d0842f560a38c7588196e721" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.48.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.48.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "bb111c5f068a4e232ceaffe5fd0b55d4" }, { "dataPath": "params_shard_275.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "d03682962fad4e8121fdf9037950caad" }, { "dataPath": "params_shard_276.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "f0aa1a680b7bc74be065c650065b74fd" }, { "dataPath": "params_shard_277.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.49.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cfdd112b54100aacfbf21a5a8edf36bc" }, { "dataPath": "params_shard_278.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9f33be62080698da0ab38fdb1e864108" }, { "dataPath": "params_shard_279.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.50.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "f9331b87e3f1f9645ad0e86f3a0e42f1" }, { "dataPath": "params_shard_280.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2b17da00d9e311d51d559d38d497263a" }, { "dataPath": "params_shard_281.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.49.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.49.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.50.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.50.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "489f55f0433c333e52ba0e07b288a715" }, { "dataPath": "params_shard_282.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "caf3354f3cabf6d79a37ce983e0995be" }, { "dataPath": "params_shard_283.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "6d7cddeccc5526a9d92e30405f36eddf" }, { "dataPath": "params_shard_284.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "bd2e2c91d315a00e0c56b42aebbb453b" }, { "dataPath": "params_shard_285.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "8e5173184d6c6553110d96f13d36418c" }, { "dataPath": "params_shard_286.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "d75816297d0cccda6c48ceb73a8575b8" }, { "dataPath": "params_shard_287.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "e8f76054be12af1a0a96ed6ad1227bb2" }, { "dataPath": "params_shard_288.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "6891efe7d24c754917686cb0766e0b15" }, { "dataPath": "params_shard_289.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ea927dab5b4afed4c21593f7c6034a46" }, { "dataPath": "params_shard_290.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "875e7a0b98caab01e4536b5a1a251746" }, { "dataPath": "params_shard_291.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "71b9c684b66ba5e0f0c3a12d67c975b8" }, { "dataPath": "params_shard_292.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "0260ee53892efa5e999ba310b8f94e02" }, { "dataPath": "params_shard_293.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8fa3f65d999d3a858feacb8d37e06292" }, { "dataPath": "params_shard_294.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7aa59dbaaacf2e8020664ce66070b57e" }, { "dataPath": "params_shard_295.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "bbbb8e67e193cf4d471ff18612144be9" }, { "dataPath": "params_shard_296.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "d21dabf30b047144d27eee0e08198254" }, { "dataPath": "params_shard_297.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "b90cc59829cb85edbd153d6782de067b" }, { "dataPath": "params_shard_298.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "713707df6e182e7eb0dbe20734d90662" }, { "dataPath": "params_shard_299.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "0bd50ec0d4f6a942d9fa27e1f4c20847" }, { "dataPath": "params_shard_300.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "586b82549a92cfa4548b5eeb0dba085c" }, { "dataPath": "params_shard_301.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "f25f25239fe4559773a9571264d73c9a" }, { "dataPath": "params_shard_302.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "c2cd3f571341f54480aa372cfaa0050b" }, { "dataPath": "params_shard_303.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.51.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "38f785c9ea39d2d2292b3bfcd3fc4471" }, { "dataPath": "params_shard_304.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "24839686d951d44772a1db9d58d8a4cf" }, { "dataPath": "params_shard_305.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "94dc9248312b92b81e6b3dbd3cc8463b" }, { "dataPath": "params_shard_306.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "a07f987a918757c0a6f8300fed2ffb2c" }, { "dataPath": "params_shard_307.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.52.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "040a1b62543fe8a568ae18b3a233ca4a" }, { "dataPath": "params_shard_308.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f3793b78ae2b8c943601b7ba3c3ebee6" }, { "dataPath": "params_shard_309.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.51.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.51.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.52.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.52.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "7c4a0786d553883db25e4448e3ff8a62" }, { "dataPath": "params_shard_310.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "5265e19b615acb012371562feac831a7" }, { "dataPath": "params_shard_311.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "51a5029ce077f17c7495a3e4b5e5fd87" }, { "dataPath": "params_shard_312.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "9fb40ded5ce2f987548d673da7268bd4" }, { "dataPath": "params_shard_313.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "a98e00698083c8db1f50ab5a529fa54a" }, { "dataPath": "params_shard_314.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "b7b330d54e6e1d0a11714b29a6efd36a" }, { "dataPath": "params_shard_315.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.53.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cb74cdd60a03b98f411f073b3db39b82" }, { "dataPath": "params_shard_316.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "196e29c7ac43965fd99a055fc5377354" }, { "dataPath": "params_shard_317.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "a6dfb1aa9810893fce8efe7a829a4d3b" }, { "dataPath": "params_shard_318.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "c815f76ff566af8d6a80d7921b342f67" }, { "dataPath": "params_shard_319.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.54.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b19fa0e3b7e360c5866f71de116f2cd7" }, { "dataPath": "params_shard_320.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2d3517115622f3507c1bbe26939559e9" }, { "dataPath": "params_shard_321.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.53.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.53.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.54.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.54.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "61856dd50bdb89946ef3d173bd3e41db" }, { "dataPath": "params_shard_322.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "d76fbbb7b5b7349e694e2df06c635409" }, { "dataPath": "params_shard_323.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "28f4fedde8f3429519ddf3b0d936b6e2" }, { "dataPath": "params_shard_324.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "f6a0f8a3172bf37c70aaec2f8c38e4bf" }, { "dataPath": "params_shard_325.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "664c4ffd6bc5b445f6cc4417eb3e0786" }, { "dataPath": "params_shard_326.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "39950d43779690571b670db6424a883c" }, { "dataPath": "params_shard_327.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.55.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "9bc487a560ee7f03d2d019b24b725cbb" }, { "dataPath": "params_shard_328.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a788de4ec58a4715ea63349cd0c29bfb" }, { "dataPath": "params_shard_329.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "0618ed7e57500f23275229b20dc6dc15" }, { "dataPath": "params_shard_330.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.55.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.55.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "535a66bd660d064752e58a047fb6f2f0" }, { "dataPath": "params_shard_331.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "916c84318d097405739245cf4305df30" }, { "dataPath": "params_shard_332.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "dcc16da600a12b534668abde53963357" }, { "dataPath": "params_shard_333.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.56.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "9aec848e62e5828ccb2dff186b820a0d" }, { "dataPath": "params_shard_334.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d8c0f47b9eef18b6113046c7a9ce5d76" }, { "dataPath": "params_shard_335.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "312a312fdc9b90b303f0beb38681a79e" }, { "dataPath": "params_shard_336.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.56.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.56.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "b90cbf3b8b1fc4f9edffc5423ffc339f" }, { "dataPath": "params_shard_337.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "24fee40b6cf552aa15c19070028e61bf" }, { "dataPath": "params_shard_338.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "a401179a5005b2b28b1a6c97fc13cad9" }, { "dataPath": "params_shard_339.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.57.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1e38e29440947183d185c73b598c5d8b" }, { "dataPath": "params_shard_340.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8558420317a4ea1d4a1f526dab3d412c" }, { "dataPath": "params_shard_341.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "3966f5e10128907a18a7220aa2f03752" }, { "dataPath": "params_shard_342.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.57.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.57.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "599d2176507e8fb396078b44f716fc5c" }, { "dataPath": "params_shard_343.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "63f9c31ff70c6a6d255c9b2af4240021" }, { "dataPath": "params_shard_344.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "076852c2bfe631acb85a0d513ed640ff" }, { "dataPath": "params_shard_345.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.58.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "63db01f9b9badb5cdf6fb6226c4b77bc" }, { "dataPath": "params_shard_346.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3ee0f31cbfbd26f4cc417ecd6885ceb9" }, { "dataPath": "params_shard_347.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.59.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "01f6adc7a488b358b7b3bf624740c614" }, { "dataPath": "params_shard_348.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "09b08c44351221386048189c0f2636a5" }, { "dataPath": "params_shard_349.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.58.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.58.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.59.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.59.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "de5df5f1b3b3474305b4de688f74faf9" }, { "dataPath": "params_shard_350.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "0be276be6d530a0cf977240193842b13" }, { "dataPath": "params_shard_351.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "7bac2e210d181d98478cf3b7306d5746" }, { "dataPath": "params_shard_352.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "9b58632084c75c6e5669046c6a112f4f" }, { "dataPath": "params_shard_353.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "45114c6869417da43707829b322beb12" }, { "dataPath": "params_shard_354.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "0c6ab09d52713c498b1df1023f808040" }, { "dataPath": "params_shard_355.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "1c2a07936a1ef5cad09f942b53f2810b" }, { "dataPath": "params_shard_356.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "df26fba3fc2a6a09b04fe108c0dc4bb1" }, { "dataPath": "params_shard_357.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.60.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "83f52274da47c26f3c4502f26dfca37c" }, { "dataPath": "params_shard_358.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6309eb1eae8d5145d241b7ce10948734" }, { "dataPath": "params_shard_359.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "b1744afe14f7d64295981aab556d239d" }, { "dataPath": "params_shard_360.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "1ec91007a7b36a22d85f9a7675d29dca" }, { "dataPath": "params_shard_361.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.61.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "299de04aad15374a20ca06902275b064" }, { "dataPath": "params_shard_362.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "940b5c19a70e8e66c9b6bad1f491d558" }, { "dataPath": "params_shard_363.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.60.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.60.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.61.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.61.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "2c0f50b94fe83de9abd4470cd0c877e5" }, { "dataPath": "params_shard_364.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "8bf68cfe4625f1ab22b3dcbd364e5796" }, { "dataPath": "params_shard_365.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "47b8977f184779f0b5393ad77a070e57" }, { "dataPath": "params_shard_366.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "4c92a62a2fe980371ed20123fdee97e6" }, { "dataPath": "params_shard_367.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "630794b467e6a99cc58ca0401dfcb876" }, { "dataPath": "params_shard_368.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "eb023aca6d45b2c143c7bc8ceb238d2d" }, { "dataPath": "params_shard_369.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.62.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cb215f83e37d15c8d69778cbb648b759" }, { "dataPath": "params_shard_370.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "720853d99902db637a1d51b1e926dd41" }, { "dataPath": "params_shard_371.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "b6713bb7cca64246779d9dd94fa44f29" }, { "dataPath": "params_shard_372.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "87e3788b7d110918dfa611285a8efa65" }, { "dataPath": "params_shard_373.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.63.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1fe613c488db66db39f39efee401184e" }, { "dataPath": "params_shard_374.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9a7abd5f35466f723f239340ba3a2aaa" }, { "dataPath": "params_shard_375.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.62.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.62.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.63.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.63.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "4a86e10a8d15a118c5264a6592ba99fe" }, { "dataPath": "params_shard_376.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "3799be207ec90fa0d9f51555c53e5d54" }, { "dataPath": "params_shard_377.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.64.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "99945b2db18ea76fae513da4a5b59df2" }, { "dataPath": "params_shard_378.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.64.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "a3248d19fbab35a12d8d63d4ad9564b6" }, { "dataPath": "params_shard_379.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "0bf953c445ab80ca9e4d4d166c8c5bd7" }, { "dataPath": "params_shard_380.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "999a2c7b4cfa71dc12f3ea9a472c92ce" }, { "dataPath": "params_shard_381.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.64.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "696623bc9a4dabee30f8d823120cf791" }, { "dataPath": "params_shard_382.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.64.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7947019eb8a236ffbdb346fdce865e9c" }, { "dataPath": "params_shard_383.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.65.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "c0f974af41f22befb754fb66ea1cecf2" }, { "dataPath": "params_shard_384.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.64.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.64.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.64.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.64.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.64.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.65.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "2d6e73d4556399acc2775b422be4879a" }, { "dataPath": "params_shard_385.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "0141de931f9f41296937c58ed54078dd" }, { "dataPath": "params_shard_386.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "a437f60cbe1c20b179c12444fc46bec6" }, { "dataPath": "params_shard_387.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.65.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "fb71b92f393234b8218316d55a83da14" }, { "dataPath": "params_shard_388.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.65.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6191e6e2a1718bacc806717188dc5c94" }, { "dataPath": "params_shard_389.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.66.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "9f2e35ba6ee25441ac6f99b6d66f401b" }, { "dataPath": "params_shard_390.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.65.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.65.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.65.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.65.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.65.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.66.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "c4ca6cf5f265a422d490ce5db72eb6a1" }, { "dataPath": "params_shard_391.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "b292c95efcf624103d4b298d72ec79ee" }, { "dataPath": "params_shard_392.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "86f8293693aa4d70091da3fddcaf6ff1" }, { "dataPath": "params_shard_393.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.66.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2517a01346670a2da59b5eca847d9575" }, { "dataPath": "params_shard_394.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.66.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dbed77dbe4748525519af7d87fe269d3" }, { "dataPath": "params_shard_395.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.67.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "5cce6f9376dd76dfd117c31ef6c283fb" }, { "dataPath": "params_shard_396.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.66.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.66.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.66.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.66.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.66.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.67.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "e69a49e3c2088df49a1b0bfb5ff998f7" }, { "dataPath": "params_shard_397.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "600a844fd7ab829a1cc3bf67fc2d6f60" }, { "dataPath": "params_shard_398.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "d11eeb6fbbd4cbfe3bb503d23a2ff3f9" }, { "dataPath": "params_shard_399.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.67.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "fea8ea91ea6fdb3cf4fa299388ebd9a3" }, { "dataPath": "params_shard_400.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.67.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fedf9150c683d25d35517615a23d3b6b" }, { "dataPath": "params_shard_401.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.68.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "62f321a3aa597faa0e4fa679cac412de" }, { "dataPath": "params_shard_402.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "168c654b5707e8315d79a5cc943d4578" }, { "dataPath": "params_shard_403.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.67.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.67.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.67.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.67.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.67.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.68.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.68.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.68.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.68.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "cd7631d594eec2e799a942075ff308e9" }, { "dataPath": "params_shard_404.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.68.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "0dd19546eb8712e1456cfcf13c8c2197" }, { "dataPath": "params_shard_405.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "a6dc10064d7b9127764c857f06241074" }, { "dataPath": "params_shard_406.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "48539d32498dde1b668d5641d759e4f3" }, { "dataPath": "params_shard_407.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.69.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "d3f17861276db1587ce53caa90c1d733" }, { "dataPath": "params_shard_408.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.68.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.69.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "00fb0afb14b2788151aac669d695123d" }, { "dataPath": "params_shard_409.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "248b10552a34623c883c53c939782f25" }, { "dataPath": "params_shard_410.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "ab889898dee6720e0cad5b3e93568d14" }, { "dataPath": "params_shard_411.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.69.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a312ebcdbeda11bb909ea1d1c9c8c900" }, { "dataPath": "params_shard_412.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.69.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "271b8b59389c4b30eb44f513fa6fa69e" }, { "dataPath": "params_shard_413.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "2072ab3734b7f6a1b0e7942242a0c7c4" }, { "dataPath": "params_shard_414.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "c43c65af6f1aa07cac4c66caac46e585" }, { "dataPath": "params_shard_415.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.70.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e73c843ba29eec4aa80a57b234516707" }, { "dataPath": "params_shard_416.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.70.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2dcd5d22fa2d8b578074d3b814511121" }, { "dataPath": "params_shard_417.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.69.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.69.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.69.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.69.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.69.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.70.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.70.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.70.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.70.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "84bcff096a2ac707967de8209ea4f097" }, { "dataPath": "params_shard_418.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "949dfa445a7bba16a68bb1c701ba208a" }, { "dataPath": "params_shard_419.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "dd59b388ce2b55b2fdaec925d7c67238" }, { "dataPath": "params_shard_420.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.70.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "f22456a2367d05924c9a758a803dac5c" }, { "dataPath": "params_shard_421.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "83c65af1b447c14ff64ed74a6c822bcf" }, { "dataPath": "params_shard_422.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "72d96114a1a1c0c3eb96f8d3b3a764ed" }, { "dataPath": "params_shard_423.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a80bf507ab53ab97843d47c0d8f3f5b5" }, { "dataPath": "params_shard_424.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "33a8d8a65bb7400b41a6673d5eb0342d" }, { "dataPath": "params_shard_425.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "5fd66a9aca1169f6be02d39eefc27b05" }, { "dataPath": "params_shard_426.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "3ac47203f369373d5d1dfd3d53f1d442" }, { "dataPath": "params_shard_427.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7421c7ac41c3f8d19059799debba9070" }, { "dataPath": "params_shard_428.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ae50c60fce014f9f621eaeb6ca145b2c" }, { "dataPath": "params_shard_429.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "9d764f19085f896a5cdd6cf6754fce15" }, { "dataPath": "params_shard_430.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.70.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "6128dee8a233acb08eedbb34cf37ca29" }, { "dataPath": "params_shard_431.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.71.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "96d51c322c970bb22be36ca2759297d9" }, { "dataPath": "params_shard_432.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.70.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.71.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "af4ab059384df3abe060c9385d93c9ad" }, { "dataPath": "params_shard_433.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "3dc571efe804a4ccd99a02d4363e8d56" }, { "dataPath": "params_shard_434.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "3894af5a94a2de5a07618dd4b8534d7a" }, { "dataPath": "params_shard_435.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.71.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6781305e7e79c9b0b0b461a8e54db150" }, { "dataPath": "params_shard_436.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5b81280d95608225f494bd0035041ec0" }, { "dataPath": "params_shard_437.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "d3ad8736907684f07e3b416488d9cdc0" }, { "dataPath": "params_shard_438.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "fb9cc34225f59eef43c26b1b21b0fcea" }, { "dataPath": "params_shard_439.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.72.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8bbbc37a584c214da4d4967924747da2" }, { "dataPath": "params_shard_440.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.72.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f79673346a0ae820a4047606b54c8a89" }, { "dataPath": "params_shard_441.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.71.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.71.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.71.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.71.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.71.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.72.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.72.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.72.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.72.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "2c77aa52174dec50c5509cede57d08ed" }, { "dataPath": "params_shard_442.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.72.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "02fffc789af36a6bf8bb7096e9a93e09" }, { "dataPath": "params_shard_443.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.73.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "b2d1459f2c8778c26278ff284552afdd" }, { "dataPath": "params_shard_444.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.72.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.72.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.73.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "5996aa292cf5db8af45c52b4e018094b" }, { "dataPath": "params_shard_445.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "47740b2af7bac54517199f30126ee1b3" }, { "dataPath": "params_shard_446.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "6c18db74b3b95d150613006b10de01a7" }, { "dataPath": "params_shard_447.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.73.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "acb7646a4a427d68fda73ebd9dcf132a" }, { "dataPath": "params_shard_448.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.73.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "af01015f67604251c8630902fe353498" }, { "dataPath": "params_shard_449.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.74.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "64688e0e490b572b40a4312de0026826" }, { "dataPath": "params_shard_450.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.73.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.73.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.73.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.73.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.73.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.74.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "409cce057ad065aa804fe38745b0ae48" }, { "dataPath": "params_shard_451.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "6a8cbf97824ed386c05c96e06fce772e" }, { "dataPath": "params_shard_452.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "133db0dd1f212823c2083ce13296436d" }, { "dataPath": "params_shard_453.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.74.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a0ecd1c79acb1d9a63473a131b463901" }, { "dataPath": "params_shard_454.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.74.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "633ab4151355ad04867f05389febfc4a" }, { "dataPath": "params_shard_455.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.75.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "825296dc4ce5a1492b29c8c1f54c1323" }, { "dataPath": "params_shard_456.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.74.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.74.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.74.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.74.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.74.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.75.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "47623b8e2573a061636f400fd8048c7f" }, { "dataPath": "params_shard_457.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "13c8df867eff32112e496cab73e4354e" }, { "dataPath": "params_shard_458.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "8f0792971604a3e494882ff7aa431f99" }, { "dataPath": "params_shard_459.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.75.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "67de623ce02605f14b0867f43b8db3f0" }, { "dataPath": "params_shard_460.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.75.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "78556e6003ddb8959b94966e6d9e8b62" }, { "dataPath": "params_shard_461.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.76.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "7f4cb25ac968f9871904ef63839a85e0" }, { "dataPath": "params_shard_462.bin", "format": "raw-shard", "nbytes": 24629248, "records": [ { "name": "model.layers.75.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.75.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.75.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.75.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.75.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.76.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 } ], "md5sum": "ec0b9837b16563fea40fbca06016f2c5" }, { "dataPath": "params_shard_463.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "30bd7bc7cee171ad6440b5fe5b6bccf9" }, { "dataPath": "params_shard_464.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "e001f1eb6186c6e64c29d3a22a94a04b" }, { "dataPath": "params_shard_465.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.76.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e11e5e0e9c1f64cac7776e9e93b085c7" }, { "dataPath": "params_shard_466.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.76.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b25a89780b8db738a760bac27c50c315" }, { "dataPath": "params_shard_467.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.77.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "796fc64cdb64a3c05c24e833a7cec701" }, { "dataPath": "params_shard_468.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.77.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a3a0e57eb8e9f4b6c9f8ceb4e893ca86" }, { "dataPath": "params_shard_469.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.76.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.76.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.76.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.76.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.76.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.77.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.77.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.77.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.77.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "4844ff4a1e5af64e93ebc774ad6829ab" }, { "dataPath": "params_shard_470.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.77.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "0bda8d0eddf31210ad43740be60f5321" }, { "dataPath": "params_shard_471.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "173ace7334cf6bf15572fb16feb21c64" }, { "dataPath": "params_shard_472.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "5fe848ba0d8d29e00f45e3d167f6e3ec" }, { "dataPath": "params_shard_473.bin", "format": "raw-shard", "nbytes": 121110528, "records": [ { "name": "model.layers.78.mlp.down_proj.q_weight", "shape": [ 8192, 3696 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 121110528, "byteOffset": 0 } ], "md5sum": "46d2537b4dbdaf8b2d8884f9da73286b" }, { "dataPath": "params_shard_474.bin", "format": "raw-shard", "nbytes": 19349504, "records": [ { "name": "model.layers.77.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.77.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 4194304 }, { "name": "model.layers.78.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 19333120 } ], "md5sum": "b34a3b7e9a6c533dfd65e473f1506b51" }, { "dataPath": "params_shard_475.bin", "format": "raw-shard", "nbytes": 242221056, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_weight", "shape": [ 59136, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 242221056, "byteOffset": 0 } ], "md5sum": "fca7e3ff2dafd0b1450d5c814767fd2e" }, { "dataPath": "params_shard_476.bin", "format": "raw-shard", "nbytes": 30277632, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_scale", "shape": [ 59136, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 30277632, "byteOffset": 0 } ], "md5sum": "c8b559777203e63cbc6ed2192b0aca17" }, { "dataPath": "params_shard_477.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.78.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "72637940ba2893dfa0340b53603d54d4" }, { "dataPath": "params_shard_478.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.78.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1e7a21bd797afc39d8804d7a2908e0b0" }, { "dataPath": "params_shard_479.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.79.self_attn.c_attn.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1297db72a73f898c6eabf75b827d2e3b" }, { "dataPath": "params_shard_480.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.79.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fc7bdad054efd584036c6100da31be3f" }, { "dataPath": "params_shard_481.bin", "format": "raw-shard", "nbytes": 29908992, "records": [ { "name": "model.layers.78.mlp.down_proj.q_scale", "shape": [ 8192, 924 ], "dtype": "bfloat16", "format": "raw", "nbytes": 15138816, "byteOffset": 0 }, { "name": "model.layers.78.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.78.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 15155200 }, { "name": "model.layers.78.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 15175680 }, { "name": "model.layers.78.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 20418560 }, { "name": "model.layers.79.input_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24612864 }, { "name": "model.layers.79.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "bfloat16", "format": "raw", "nbytes": 16384, "byteOffset": 24629248 }, { "name": "model.layers.79.self_attn.c_attn.bias", "shape": [ 10240 ], "dtype": "bfloat16", "format": "raw", "nbytes": 20480, "byteOffset": 24645632 }, { "name": "model.layers.79.self_attn.c_attn.q_scale", "shape": [ 10240, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5242880, "byteOffset": 24666112 } ], "md5sum": "fdf81334d63a531516aae9af55070323" }, { "dataPath": "params_shard_482.bin", "format": "raw-shard", "nbytes": 4194304, "records": [ { "name": "model.layers.79.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4194304, "byteOffset": 0 } ], "md5sum": "1ff28d154a082e407bb8d984fc0feb73" } ] }