{ "metadata": { "ParamSize": 805, "ParamBytes": 36381212672.0, "BitsPerParam": 3.4891900844756822 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 525336576, "records": [ { "name": "lm_head.q_weight", "shape": [ 1024, 128256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 525336576, "byteOffset": 0 } ], "md5sum": "a65f7121bbf8b8d868ec27261f0ea394" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.78.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "079916373e8439416b26c803021590f2" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "4a467f55386145a23ec568e5b475acdb" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.79.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e10f073ab500b9280d273a5591669093" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "db57537a4275e462d06b49369f058c30" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 31145984, "records": [ { "name": "lm_head.q_scale", "shape": [ 64, 128256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16416768, "byteOffset": 0 }, { "name": "model.layers.78.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 16416768 }, { "name": "model.layers.78.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 16433152 }, { "name": "model.layers.78.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 20103168 }, { "name": "model.layers.78.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27443200 }, { "name": "model.layers.79.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27459584 }, { "name": "model.layers.79.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27475968 } ], "md5sum": "c9935a365acd087e52becaa962536a22" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.79.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "21d25ba3ebb409cf8cb942c3ca15c871" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.79.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "61864aa3de8b994bc547a7da612bc177" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 525336576, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128256, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 525336576, "byteOffset": 0 } ], "md5sum": "19bb7d1345a41484942df187882e72cd" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4385b3eec159eb8924eb4fcd346fc255" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e3cf6990f2359e255ff30327fe225226" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 29835264, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.79.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.79.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.79.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.norm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.embed_tokens.q_scale", "shape": [ 128256, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16416768, "byteOffset": 9732096 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26148864 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 26165248 } ], "md5sum": "7caa9736dc48afa478de3ce7bcd123b6" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7e7fa5c2a28d6189a8a3e0e44b93c7a9" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "25c50f413c669352f9fe083f99df24ff" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9d7409d626896665cd2a7f7bd23783c8" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6fa627de17d7d5a9265395f9e5985e57" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e6e058383bace8c8b8a1a44266108aae" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3551358a1946ef0074b4605d9ffa4067" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b62d95a534623dbb7ac2c84ea7d29b23" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "10bb311d31a89b332978a6ef1c93d029" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 9715712 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 17055744 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 18366464 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19415040 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 19431424 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "5637c60218ef6a5acbc18e5358e20c6b" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7b1523bd56a76ccc5420b16e19f8950a" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c664d357dd39cf8309ad73799404d5e5" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d913fb3661e40e94a6b06cfc4a374a73" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d91b06ddd90bb0c98e265b6c5d37e7ee" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "61432b6af07ce8300abcb8498a1b37f5" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bf8571b565285c13c5738e5af9b6dd30" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "58e4bc58dbf9180d62e4ab440382e2be" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bd29056507389a2168c12262bf8c2984" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "459c8f19196e5e0b8f90bf65f7d02035" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "424982e2737949f21173ee0027152722" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 29163520, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 24428544 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 25493504 } ], "md5sum": "f4ebc197f285a586dc473431cd70b8d7" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "fff435ef77ee67b7009decfbd85ed635" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c87689882aebbe8ee0e82ef873f30f53" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "eda41186789b7b630bc766a8fcf3ed92" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ab6f74ce49f74d77635fb2085b9f36ca" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "31df8d1d2c72b02ccf970a06e3cf06b2" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e5f1146267aca13b2413ce248382e211" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "19839cd95d91874923b6e3668c64efd6" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b3727af0bab99a27b512a132d063a363" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a1cb61616690137c47788b6f0b5ab0f4" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a0e04a7c7e61809bcecd6bb237524f30" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 32833536, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 23117824 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 30457856 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 31768576 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32817152 } ], "md5sum": "7a0f439ee39dfb0834f96a3d7656fdab" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9c22c9791b36f7d7130ee135c44c13ed" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2f795ab7dffa6d6aec6d8ecea4c08f80" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d688d4bb7774d53ebf3c7df759415d77" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "895ec78beaf86813dec6271a9fe7d8d3" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7e026a2f5470b98e1ee0863ac7169019" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "897ab178a94d32fc5b411601720fae85" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a07b062e6b12cfe5aeda52e7d132b1b9" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 28147712, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7356416 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 7372800 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11042816 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11059200 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11075584 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14745600 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22085632 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 22102016 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 23412736 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24461312 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 24477696 } ], "md5sum": "486586a5ed545b44cfbfff0196f94446" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ccc6b5a6d61a7d38f13c5c50720ec74b" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6f2ea4b46f95a964ce85f62c8841f077" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "874424c7a11be564544f023d0fc5e66d" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4bcd9d986b55e73164fefb81fd85ce9d" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "1ee68df07b01513df401b7bd27a4d53f" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "238fd10527f39aefbd96cf9aeec84c19" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "10bc6b383a0ef458a002a74a4a0d8533" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "233cfe1b2f6251009f2e5c376ae49b18" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 9715712 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11026432 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 12075008 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 12091392 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15761408 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "1cbb7992d099992979eb45229a094d66" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e76744d8869155d7ba396cef7b4e469d" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "59fc2957d0b7b8ef918b73d35808869f" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b5252a71aadd6a5d65cfe3e1af2ad3ea" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "decb1f74d6b7780c1bf5f58d3dc925af" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a10a2e835e64746cee643df5514bf13f" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "62a1fb1d9d15e07aeaa05864f6c1979e" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5d75c4a3b2c7245ac2e8b10df5b33931" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "90b32b90695635b8bce07d60a95e211d" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "51ae7ded98490d7d1390fdf24b29d07f" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 28114944, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24428544 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 24444928 } ], "md5sum": "8b2bd2b086ecfc0dc6e343434401df67" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "52209f9eae10e50058598c9738f795c0" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "46ad35ec9b89b0726a302c10aa41ddd2" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6a8457909af459f3867a4cafdfbd0478" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "90d3c31af2efd5b3e5dfb092243b8229" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5beb0a8f9d793af02a87c36bf63b68e2" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c19a628173d75a4548db8bb78a49e49b" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7e59e393075f24b698641489fefaca68" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "70dd0d58570e814802621fdf41c80516" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 32817152, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 7356416 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 8404992 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 8421376 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 12091392 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19431424 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 19447808 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20758528 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 21807104 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 25477120 } ], "md5sum": "0028ee1956ddf06c33f4cf64ddc2f029" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "da9272f8f2e80c28c9de0866664b8f45" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "46884fb006fe62957bf54f1d444080b7" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "424a3ab4029bdebd40fe6c3112fde6f2" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "44354e9c7d871b1191f963b428f56474" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5395e460fece233d880f229d4f6b65ca" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "83ea770c5566f7815f9a0b532df4b752" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "cbfac70d672977e68bec1a9b19c3f34d" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "07243a39d5d6c7bca3c415aaa201b996" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3187524e781e1cf85278fcb4853391fe" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "68ff0bf5940cf94b90ffd0e1082bf50b" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 29196288, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 1310720 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2375680 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2392064 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2408448 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6078464 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13418496 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 13434880 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14745600 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15794176 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 15810560 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 19480576 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26820608 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 26836992 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 28147712 } ], "md5sum": "b0464fe0f2c5ae8c1c6cef05225c7af7" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b285268e3e170f8e0672507132d5e5eb" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6bee485fe1eeeba530fa091041765705" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c7a7b4aa23817b52eb19079f6e209095" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "63ea476fec6dc52eaa59085b21fbac4d" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "16484046269996c75abe52dfa77c217b" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a333f3f806ec5397a8e86c20f365f300" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "76b83ea0013c6d397c6593daccbe2b93" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "555749486d47169aa63132849b28d4d9" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "efe4a491fdc5ed71271e290639d004eb" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 30490624, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9715712 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13402112 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 13418496 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 17088512 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24428544 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 24444928 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25755648 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26804224 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 26820608 } ], "md5sum": "0c997f609fd44e7770fd124771421496" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4663d733b6b863472eab8554b83174f2" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "16da0a07eb9ff4e11e2e8b42fdf551f5" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "93fb9871c9669e2c72bbf4e5e8879c78" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d28e1f3403430b913452ec32f7f4537e" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "afc08b0725f1157fb1d53487272ae7a4" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "15431e1cbaac5ba16c842159477a2f32" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ce72745c774e7c094664024f99227824" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "974a5045bd59d69c670454f235f46640" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 9715712 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11026432 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 12075008 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 12091392 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15761408 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "59f872a77ee3b7e45c42b4c323302919" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8d9970ea5695a126d1536dba6a7f5ec9" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "39eafea562df2a5ceb7fcf21897896c7" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "77a32e698f40d5472005e089f893ef81" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "791c1e45b9e2d657db1faaac6b887083" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1532db18778b67e5c5e7676a9c737c55" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "00927663ebfcf61af2907e59362ae58e" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "185afd3fb699c021e291099c0a38d7f7" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2969c1423647885127380f9ddddedacb" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "12f2c88470f85706847dbf687fe7e7c2" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 28114944, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24428544 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 24444928 } ], "md5sum": "e64ca288ab0a2d77627406946cc8054d" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bb597add15cda85714890bd803712cd2" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c62b97b056f2a2b8c01319957c82190c" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bd0aab9daac986182e8c6a1d573aeaba" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5c47dd63fc952ef3b20433de0532c46d" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "34d21e3f2fa57455c81ea8bd0c951cba" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e0638ba0a1b31900a754f8b4756b16d8" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c23d4db5fec8c8262dea715768d429d0" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "bfd6f7c110d7f638c06ccdbfd404292d" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 32817152, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 7356416 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 8404992 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 8421376 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 12091392 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19431424 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 19447808 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20758528 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 21807104 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 25477120 } ], "md5sum": "7fc9a6fcbc061712387aea0d8d79bfb6" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3377c652b7947a8779fcb825a124d6dd" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0e562d9fe7a780f238f1963ffb3aef2e" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a93fd0e453b3858877672089ec190d70" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cb56021bd2ebbf01533229cf7da71dda" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "295017ccd030c6465e6f9f4148b863f5" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e5858146aa76940994b5ff9fdb0229a4" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "45d3349c4f19f5315f2795f4f1777d30" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "86f5729b4febad86d0c5a3102a7228e3" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f2471243f3c41b4d037f22f21c29018c" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bb4c0980fd073d3cd82b72859a5d2003" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 29196288, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 1310720 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2375680 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2392064 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2408448 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6078464 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13418496 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 13434880 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14745600 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15794176 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 15810560 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 19480576 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26820608 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 26836992 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 28147712 } ], "md5sum": "1c8a135f82d939e3710435acde44cd5e" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2464186b085595e1823554f265d3029d" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0e69f17fcb15ca19095227d19febcdbf" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "18462f370054075105ed9f9c856b4d17" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "bbf2604c6486780edf6d85ef1013067f" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c6919f02cf8e6389b99d646422060b56" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7134a0b5da2f31685532ae6e8905c8d8" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "050cc916aab9db40f95c239811c28428" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "7ebe268884c952c68a044b433e646ddb" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "2782897d6a93c1f8f577653a0f58de5d" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 30490624, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9715712 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13402112 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 13418496 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 17088512 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24428544 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 24444928 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25755648 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26804224 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 26820608 } ], "md5sum": "23ef91b2760197134016331f3127b176" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "bcea0aa1d5114a8cc9e0f5a8f01c0f0c" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2872e98c9340973c5b7f48173eecc27e" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "89e7a172f180ad17486ba1ef0f32661f" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "aa7b18257721bc2d12878d6be6e506bd" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c8dc27111621bd20f6ee4f7a82a4a3f3" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "81acabf88fc63dcce5cfd079d6070cd9" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f995db5e4b30f36c4239a105ba64868d" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5a2f411dc7c53b49690f663f8dfe5faa" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 9715712 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11026432 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 12075008 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 12091392 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15761408 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "c45bdd15806391a392a758bd1f23020c" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c826963d22d1a25a3e75d4c68d1e8586" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f9bf34fa6c07391207497fa2460417bd" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "75beae32aa3e622b728208f997c859de" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "234c4b659daee5c288fcb6a72ccf0de4" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3cac40cbdaf1b2929d8f6d2e5ed0f91f" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c3b077c535f7feeb323902d66837d739" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.40.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "838fc9831170876bc3065d17dd8daa19" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c192e7944f8cbb13f0fb125542311b77" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "25e728112dde9b61ba13c428cbee8c0a" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 28114944, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24428544 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 24444928 } ], "md5sum": "ef3756c61d09940b77e620e3c27bfd6a" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c6dd71e5db5f49925206ff3c4ab34ba3" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bc1cd9af077e53b2bf4131e61b622349" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e8b54f5e29eff139cd679e56b9754c59" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c0353c4a35c5f09cdf546a8fb9868fb6" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9d6949dea0f5a27567046f9542d593a3" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "1b86008f60aebde99e19a040a4e16c34" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8aa2af8430cd7b521d4ad88c0ed678f2" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c424528dad1d732f494782338617f63d" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 33112064, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7356416 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 7372800 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 11042816 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18382848 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 18399232 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19709952 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 20774912 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 24444928 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31784960 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 31801344 } ], "md5sum": "524b28b24bebd810febd852f250df9b5" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a6dd04f69e197a89446c67f850feb5d1" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "007bc0099bcb00d042632ad6b6f26574" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "21ac5ffcb4da5bbf89fe7c2346ae7a2f" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9395c2f45f506c8ab0960eaa3ad5a206" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3c31460f949db2db5332e84c6833325c" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "42e8d0a25e8186d76c3d23644854fa44" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.41.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1f665af0a917d13af70d3bf8df0de2cc" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0a99049d8e4c939a3a9b76e9cb910d7f" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3fa33fc63a4528b7a3d122bd3d986c07" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "fcd51b0e34176263a3fe66cc6100a7c2" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 31522816, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 1048576 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2375680 }, { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6045696 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 13402112 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14450688 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 14467072 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 18137088 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 25493504 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 26804224 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27852800 } ], "md5sum": "0aced6ec132e5a579419ae33390f6090" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.42.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c5bcf4c1a716c488c9f02ad680686639" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ecebde62a42541dcf4fc5faf04ff55d3" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0ddf0f740ef9c6f8df6564d77c2ab402" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "932b85f0c1eb7e604db6d6b3e40eeff6" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.43.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "df4f51e223d3fbcd722d674b17b85b72" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4e17ee1aae920da61040de20c942e809" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b6e94af2ee42fd9790798cd0ddfdf85f" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "33db141ebeac57146df0af670aef18a6" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 26820608, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.42.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9732096 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9748480 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13418496 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.43.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20774912 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22085632 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23134208 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23150592 } ], "md5sum": "2bc6d0ea37ca9bbb3c227dd670511409" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.44.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "32ca45f8f98bcf29a6ef5da084a2b3e1" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e6a6601776abbd14b09a133ef5dd569c" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "72d3d57b65fa4cd2a277167bf9bf6829" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.45.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b0bb6195e7884950a91d9925e20aeb0b" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6cc4807eed1349104fd28160fad7e631" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6d4abed9881234788150b5edc5b1cbbc" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3a9fcf6332786f36e7cc54c1c8f02cb2" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e20d5c9975b750c415dabc80e7957401" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.44.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 9715712 }, { "name": "model.layers.45.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 17055744 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 18366464 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19415040 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 19431424 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "ce4bd8fecedadaf835ba3fee134ec186" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.46.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "433ab37263ece443ee3c28f1a95a623e" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ed26d6c68fb958bd9ae4cecb7a58f83c" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "936638a30e6702e2793138f624629c27" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c000057abc4ffad2dbbb48bd4f197fe9" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.47.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "56648df5027134d9084144b5880669a9" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "51d5762944d32e4d1487c48eee4f1d17" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.48.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8f10f8bedbedbfcdcd72c8a07b0854bc" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6db733fcab6507bda496c3100274d280" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "1bf7ad7387ba1e3c233ec7b77cc9063b" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f10e732250d045c0a89c7400bf81ba5e" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 29163520, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.46.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.47.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.48.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 24428544 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 25493504 } ], "md5sum": "e142d92f388a664851dc507d6c76aefc" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "29bae3b62083c39b78c1ae447438ed6b" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "71cf4e1d3c705e24a610f0ad5f29d2dd" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.49.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "790b0b646a0a79a234f97bf91faee87d" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7dfd52df71947ebb319f2d4073df34d9" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "98eb45f227f35655f4cfbf7bd5011ba6" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "1c8b4e7cc8cb93be0e5ec65431de17fe" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.50.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d1ab90b450c3d87b05cd1f778e751e58" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a691e0de61a67925761ddbda160067a9" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 33112064, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7356416 }, { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 7372800 }, { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 11042816 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18382848 }, { "name": "model.layers.49.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 18399232 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19709952 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 20774912 }, { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 24444928 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31784960 }, { "name": "model.layers.50.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 31801344 } ], "md5sum": "65c4acfb580882ab2896e6692d62c39c" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.51.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6e9434cdd79e4e0cfe6c101f135187ab" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ea6abded8d1b7d2acd268650f7dd4489" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bd71205d5177b0866e387afa10db7816" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dc6ed92ee858776ebf72fdd72aee82dd" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "cd98b15d42e4a5a8f6f229787a5fddb5" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d41202bb9b3d09f6676b79cc2b6e57fe" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.52.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b8ad45e2ac9716818a10e8b8a4c6f832" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "339dc6d977c497afebf968616d3d674c" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "84f2de941e6fdd7088fed2743f392e3f" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "1915b8879ca438c549cc6689093802bc" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 31522816, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.51.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 1048576 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2375680 }, { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6045696 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 13402112 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14450688 }, { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 14467072 }, { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 18137088 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.52.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 25493504 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 26804224 }, { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27852800 } ], "md5sum": "4931483cdb2adbe14da2f5c34657b214" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.53.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "38cf9b231d89e347544de8747ffc37ea" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c8f78c17c0c479e1c87598aa92cdb1b9" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "924aa14eef39925da99f3bf8cd838955" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "0184a2a95b26a1cb956f915c8cfd7fe8" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.54.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "591e2781d81e0dfec20bc2e123524cd3" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2db7c99e5245c420f5c4f3d0a6439552" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "26f8ccb72e1ace2d442ad1d622cd3417" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ed7eaa4bd8b058e684035bfb36f26f12" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 26820608, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.53.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9732096 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9748480 }, { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13418496 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.54.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20774912 }, { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22085632 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23134208 }, { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23150592 } ], "md5sum": "e0a9fd76b3f017559938996902c2b0b3" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.55.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ce4ca479d943d06e729c1572996877bf" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5bca160fc0db7f86286e2498424b4ecf" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "63fc0505ac44d485d77462ff7d00fdd3" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.56.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "fb581f9ad7e15603e91aba3c78571aab" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "29e801813798f75d407a6315b6f01d96" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9aaf7dad94faba4f3d356d6daea7519f" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "206a81dd9e934130303eb22c484cd245" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "32aef920f1c4a3ccdc13e13c5d503f19" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.55.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 9715712 }, { "name": "model.layers.56.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 17055744 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 18366464 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19415040 }, { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 19431424 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "8d7c600d10d19c5b0fb9e53be77c6b8e" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.57.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c4cfe5926ed035733948ab4926604bca" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f0669876921c273c771bf838b3f9dfe4" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "86b01e5281b807b4bec63e95dede1c3f" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ff3418763e83d7cb8d8bffee086c8711" }, { "dataPath": "params_shard_259.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.58.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "9a1674d242d71caffda35d4044e2e6d4" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a087457f274ce3efa70a6b082f95db0f" }, { "dataPath": "params_shard_261.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.59.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3e947d986d7f68b02026a813966d6a75" }, { "dataPath": "params_shard_262.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2ba2a7dbc00e86e3a510d2041f6deb45" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2bcdee34cee1ec2ff10a5b46ddc7e68f" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "1f3e09f5b7c5e63209dcbf9f39be1ac7" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 29163520, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.57.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.58.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.59.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 24428544 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 25493504 } ], "md5sum": "fb959746a3bf5517c9f2655d57a16a1b" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "27ea1a7501b47563757cd96c7460ef39" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d526356a1e2650460ba0db853b6fcffc" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.60.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "497d49d7251862c72c14ce1b2297fcfe" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2abf0a56395284422367ab7fc159fdd0" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6c2be5cd8e48a5fc5d192ddc63ddc665" }, { "dataPath": "params_shard_271.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "75390dce32f019f66a1f832ba7a50c0e" }, { "dataPath": "params_shard_272.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.61.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3c10070dd5cfd06c28c6aadbd4f30f3d" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "90c15c3bcd5e58f38dcf17c3a6e436b2" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 33112064, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7356416 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 7372800 }, { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 11042816 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18382848 }, { "name": "model.layers.60.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 18399232 }, { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19709952 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 20774912 }, { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 24444928 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31784960 }, { "name": "model.layers.61.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 31801344 } ], "md5sum": "ab54ccaa04e79a0fa3148d2278de5e91" }, { "dataPath": "params_shard_275.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.62.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "dcb2755fd9c420f63ec3b104b47a0c15" }, { "dataPath": "params_shard_276.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "00cb242a6812248d1f67ecd4edeb893f" }, { "dataPath": "params_shard_277.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a20ababb2ab9a31237bd38bebdaef437" }, { "dataPath": "params_shard_278.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "09b31afe918501ce2b9ddbdb429667d0" }, { "dataPath": "params_shard_279.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "42e46f42c8c9e18ebcd417ac5c0365af" }, { "dataPath": "params_shard_280.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bda44f588564533538efc5e8a560df68" }, { "dataPath": "params_shard_281.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.63.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cd6e2902c36489d7038a6ae863b1ade8" }, { "dataPath": "params_shard_282.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2419629c93b01b3505be69eca7ba741a" }, { "dataPath": "params_shard_283.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.64.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "548dfdda7b7bdea46e706e64ac4f7da2" }, { "dataPath": "params_shard_284.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "11206a49582fcc69a28989df290726aa" }, { "dataPath": "params_shard_285.bin", "format": "raw-shard", "nbytes": 31522816, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.62.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 1048576 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2375680 }, { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6045696 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 13402112 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14450688 }, { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 14467072 }, { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 18137088 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.63.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 25493504 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 26804224 }, { "name": "model.layers.64.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27852800 } ], "md5sum": "82ca679049a1e5097c214e7fe8abd6bd" }, { "dataPath": "params_shard_286.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.64.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4c8ed961aa7d1e22d01f75041ece9e04" }, { "dataPath": "params_shard_287.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.64.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fd117d6edb79ca859383c33fb4c49a01" }, { "dataPath": "params_shard_288.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.65.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5eb350bc14c47bb74fdad1032fbe23df" }, { "dataPath": "params_shard_289.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "52d56b07ba965eb0b17261fb030b7ba0" }, { "dataPath": "params_shard_290.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.65.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2a164be4504de844a53fd4dacec9fdde" }, { "dataPath": "params_shard_291.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.65.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "401d5d6ea1724b2ef5770cf30e6b6571" }, { "dataPath": "params_shard_292.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.66.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5d8f00629686623ac722842cc1d851a2" }, { "dataPath": "params_shard_293.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d00c55e927af6f2ef990be12411d5196" }, { "dataPath": "params_shard_294.bin", "format": "raw-shard", "nbytes": 26820608, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.64.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.64.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.64.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.64.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.65.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9732096 }, { "name": "model.layers.65.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9748480 }, { "name": "model.layers.65.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13418496 }, { "name": "model.layers.65.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.65.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20774912 }, { "name": "model.layers.65.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22085632 }, { "name": "model.layers.66.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23134208 }, { "name": "model.layers.66.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23150592 } ], "md5sum": "bb828b260bedffdffc62b9c5806257d8" }, { "dataPath": "params_shard_295.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.66.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e47feceee237d279906db2df0c89d31c" }, { "dataPath": "params_shard_296.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.66.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "17ca704ca685ce2bcc858472543afbe9" }, { "dataPath": "params_shard_297.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ef57c83fb99d46279cdd2e4dd719b16b" }, { "dataPath": "params_shard_298.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.67.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "441e5a67c328628c0ced18d525af1184" }, { "dataPath": "params_shard_299.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.67.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a605a27d8bff1b521919ba165f1196c2" }, { "dataPath": "params_shard_300.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.67.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "7d6f6599fec9687046afb4c9580f6d0c" }, { "dataPath": "params_shard_301.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.68.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "de0fb23d745d52cc480f5f7470685d95" }, { "dataPath": "params_shard_302.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e9b857c4e4e280816184ddcdd1299b06" }, { "dataPath": "params_shard_303.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.66.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.66.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.66.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.67.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 9715712 }, { "name": "model.layers.67.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 17055744 }, { "name": "model.layers.67.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 18366464 }, { "name": "model.layers.67.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19415040 }, { "name": "model.layers.67.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 19431424 }, { "name": "model.layers.67.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.68.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.68.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "71817ce6be6f787efe9bbe0b88d6f4ca" }, { "dataPath": "params_shard_304.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.68.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5f0a33af894ae0a56da82c06f5a79600" }, { "dataPath": "params_shard_305.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "32ae23b6e3caea4fc5246aca49ef3da3" }, { "dataPath": "params_shard_306.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.69.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b4f90e3995f559d222f7b954c2803e11" }, { "dataPath": "params_shard_307.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "53b66f34862e2691a861e9651c91d8c5" }, { "dataPath": "params_shard_308.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.69.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "bb9481f9f21f721a4afc902dccab6906" }, { "dataPath": "params_shard_309.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.69.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6a0fc12629d1ecffafb68465511bfd40" }, { "dataPath": "params_shard_310.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.70.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b11171824779130af654a9f4e924ac92" }, { "dataPath": "params_shard_311.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.70.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "aab22d1ea69a25413cdd2c9338630f61" }, { "dataPath": "params_shard_312.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e016d02c69b6e001e36c2400053e6463" }, { "dataPath": "params_shard_313.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e70aeac8ec56fbaad1efda97371892de" }, { "dataPath": "params_shard_314.bin", "format": "raw-shard", "nbytes": 29163520, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.68.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.68.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.68.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.69.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.69.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.69.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.69.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.69.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.69.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.70.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.70.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 24428544 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 25493504 } ], "md5sum": "7e494d5d4927765aca6205e16c605901" }, { "dataPath": "params_shard_315.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0d6c69e26423107b385540e2c5a85ecc" }, { "dataPath": "params_shard_316.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "a7ec584c19ef5abb16aef8cc28865b93" }, { "dataPath": "params_shard_317.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d172fde4fe457af144b17c201e425863" }, { "dataPath": "params_shard_318.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "f1bb7c700847b3f428487cb43a9e6f3e" }, { "dataPath": "params_shard_319.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "66c9c6a95c6f6d83c91a155548912f9c" }, { "dataPath": "params_shard_320.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "363483e66999506be0bf55f12dc9d343" }, { "dataPath": "params_shard_321.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "011ccb5bbcc055edf27ec512d1f9c572" }, { "dataPath": "params_shard_322.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "002b06578c697b0d580179c6c0ae45e7" }, { "dataPath": "params_shard_323.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.70.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ec8f8170763c1df518e471200238302e" }, { "dataPath": "params_shard_324.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c3285a985f2d5968904a3581e3d295eb" }, { "dataPath": "params_shard_325.bin", "format": "raw-shard", "nbytes": 31522816, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 7356416 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 8404992 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 8421376 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 12091392 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19431424 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 19447808 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20758528 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 21807104 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 25477120 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 26787840 }, { "name": "model.layers.70.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27836416 }, { "name": "model.layers.70.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27852800 } ], "md5sum": "94d6be65fb564c792f79477de8348e89" }, { "dataPath": "params_shard_326.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.71.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d499e921b868c57337a40b5e4567cbb5" }, { "dataPath": "params_shard_327.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9e473164e368d7a6608c4dcdbf3f4e70" }, { "dataPath": "params_shard_328.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.71.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "422d4d22894d26fa27e18aa5b8ff2153" }, { "dataPath": "params_shard_329.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2a9008d3684f47bf7584b7fd8dccb9bd" }, { "dataPath": "params_shard_330.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.72.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d551c573fe158791ef607f99e1335bf4" }, { "dataPath": "params_shard_331.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "4d8ddcaa3e0ae6ebcfc23e72d606526a" }, { "dataPath": "params_shard_332.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.72.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e55d7e8ae84c0415a57da1d04ce030cc" }, { "dataPath": "params_shard_333.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.72.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "49f45fd9c20ad61df130502b594a747d" }, { "dataPath": "params_shard_334.bin", "format": "raw-shard", "nbytes": 33112064, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.70.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.71.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7356416 }, { "name": "model.layers.71.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 7372800 }, { "name": "model.layers.71.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 11042816 }, { "name": "model.layers.71.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18382848 }, { "name": "model.layers.71.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 18399232 }, { "name": "model.layers.71.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19709952 }, { "name": "model.layers.72.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.72.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 20774912 }, { "name": "model.layers.72.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 24444928 }, { "name": "model.layers.72.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31784960 }, { "name": "model.layers.72.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 31801344 } ], "md5sum": "fe062af2ad056762b6f62ca2f41ae99f" }, { "dataPath": "params_shard_335.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.73.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a05a9b38ce653f175bd516e518cca02a" }, { "dataPath": "params_shard_336.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.73.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4cf2d488c83e25a77ed52b62909e9743" }, { "dataPath": "params_shard_337.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "86bb7c308c361b913f8a70a09b38383e" }, { "dataPath": "params_shard_338.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.73.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "60bdb4e85f228f942a57899b26102700" }, { "dataPath": "params_shard_339.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.74.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "461adaa60ce741d00904deb7455fe699" }, { "dataPath": "params_shard_340.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7c438dd9ee4c966d36dd9df33f74f706" }, { "dataPath": "params_shard_341.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.74.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "03ffd4a40257f12f73aa958cc5f885ff" }, { "dataPath": "params_shard_342.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.74.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bd209916cbcbfdec8d7162a9d8e5650f" }, { "dataPath": "params_shard_343.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.75.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9cbfde261c3a603c929efd2cadece7e5" }, { "dataPath": "params_shard_344.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9e6707c455195f4a2f118bb73eff1228" }, { "dataPath": "params_shard_345.bin", "format": "raw-shard", "nbytes": 31522816, "records": [ { "name": "model.layers.72.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.73.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 1048576 }, { "name": "model.layers.73.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.73.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2375680 }, { "name": "model.layers.73.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6045696 }, { "name": "model.layers.73.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.73.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 13402112 }, { "name": "model.layers.74.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14450688 }, { "name": "model.layers.74.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 14467072 }, { "name": "model.layers.74.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 18137088 }, { "name": "model.layers.74.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.74.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 25493504 }, { "name": "model.layers.74.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 26804224 }, { "name": "model.layers.75.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27852800 } ], "md5sum": "53ace84587da37ea76bd089a2750b398" }, { "dataPath": "params_shard_346.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.75.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "02f613bf9e238c4478c4d8c6ce27c6b2" }, { "dataPath": "params_shard_347.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.75.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4f7cbbd00966e6c713bfb390b2d9fd89" }, { "dataPath": "params_shard_348.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.76.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8becf49f49891f37c7c85983e54dac26" }, { "dataPath": "params_shard_349.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "561071b675d91719dde7a7d355a1ffc2" }, { "dataPath": "params_shard_350.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.76.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d0887b8c1e802678ea66b00dc5b20095" }, { "dataPath": "params_shard_351.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.76.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "44aadc08fc7aba695d1b6a8831a01299" }, { "dataPath": "params_shard_352.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.77.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9d22fbf43fbd15319797f1300a97d580" }, { "dataPath": "params_shard_353.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "82bca534904e8cdc7bd30a63c26f17b1" }, { "dataPath": "params_shard_354.bin", "format": "raw-shard", "nbytes": 26820608, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.75.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.75.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.75.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.75.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.76.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9732096 }, { "name": "model.layers.76.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9748480 }, { "name": "model.layers.76.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13418496 }, { "name": "model.layers.76.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.76.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20774912 }, { "name": "model.layers.76.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22085632 }, { "name": "model.layers.77.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23134208 }, { "name": "model.layers.77.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23150592 } ], "md5sum": "2991b658ef69d55c2b569d284ae7dafb" }, { "dataPath": "params_shard_355.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.77.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a396385c8e03960a570997f1e1bbc92b" }, { "dataPath": "params_shard_356.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.77.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9226ccc8ceb797ca826f815c73a5bce4" }, { "dataPath": "params_shard_357.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.78.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8e22cc94f7505466a1c0496707316856" }, { "dataPath": "params_shard_358.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.78.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d6ecba2346ee124625ae1c6fd43b9c29" }, { "dataPath": "params_shard_359.bin", "format": "raw-shard", "nbytes": 12075008, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.77.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.77.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.77.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.78.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 9715712 }, { "name": "model.layers.78.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11026432 } ], "md5sum": "8c1086647ed476abc49df2a716e4346c" } ] }