{ "metadata": { "ParamSize": 313, "ParamBytes": 4760885248.0, "BitsPerParam": 5.0011817065612245 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 272498688, "records": [ { "name": "lm_head.q_weight", "shape": [ 152064, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 272498688, "byteOffset": 0 } ], "md5sum": "c6090dc83091739c31db89baa2b599ca" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 34062336, "records": [ { "name": "lm_head.q_scale", "shape": [ 152064, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 34062336, "byteOffset": 0 } ], "md5sum": "82b34d032af0c5e6c9aba005aea115dc" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 272498688, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 152064, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 272498688, "byteOffset": 0 } ], "md5sum": "679a6384deaf5483e97bc93bd7219bd1" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 34062336, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 34062336, "byteOffset": 0 } ], "md5sum": "b1c56de3d9d14b7dcbdf70de22eef5f0" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "82bd43d2191d1d7f775e659e925c90c7" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "2f8e8ecc9c484d45d85606110466eff6" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "5a1f6a084302004d1295bb43f280be14" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "7d8a7f8bf1f13cd4761945d8765cf128" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 33519616, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 7168 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 4250624 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 12737536 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 12744704 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 12753920 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 21011456 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 22043648 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 28466176 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29268992 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 29276160 } ], "md5sum": "aea3f8be8b8882db3a4234173ce314ed" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "04c74282a8758f59f645743a88be9200" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "7b2c7bde0041b77d9ff50e67d9e1245c" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "4cfd3f44bda97281fd1c3cf10fcf8e45" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "3b2ae0ec0e37867c1bfbedbee24435ac" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "1bf1ac81a6e1a4ac9da16ae47bd35f50" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "cbfca11f871b8d6908c9c470659f1f7a" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "ac0033f23ce40dfefdcffa70e184e512" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "ec11fd17531d2529a5cb3eeeccf2f927" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "47df53f8e307fdc0c15f2cc42312b3cf" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "24395ead1cf3097dae04087aa5d4b8b6" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "e452a8a7a8054110859250de8a7e27a2" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "1633203b955f26ad6430b4242c1197b6" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "4b7ce5bc5200b33b1592746f437eeb6c" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "83f4e8795a07a1d9af108985f11f283c" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "84250ee2c0630f5516b5529b09346467" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "8589be6098ad7b54f31ebecb1868094a" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "21974fcc49c5474983d0bd5abe5ccc81" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "909a202ae882521e4419e33095137ccb" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 33285120, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 25018368 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 25027584 } ], "md5sum": "7244eaa63d285bdc953c82ec69f07faa" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "fa4d4b0be34fb1e37e280b96e53b4dfd" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "80a66f39d948050ccd128929c9fffd11" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 30301184, "records": [ { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 1032192 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 7454720 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8257536 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 8264704 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 12508160 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 20995072 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 21002240 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 21011456 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 29268992 } ], "md5sum": "6262b70ac382d94773c7b9b6d7039171" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "5ea3565b77ad3da108feff9531a987d8" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "72c1c6ec7d6bd72f631c78f36adcb6d8" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 7225344 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 7232512 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 11475968 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 19962880 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 19970048 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 19979264 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 28236800 } ], "md5sum": "52044819a3abc39d5435685c19a8b38e" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "db75f5cc7e59a61e4d79f94be2e23298" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "766e41b13d6ca7c9557d0930c7818089" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 7225344 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 7232512 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 11475968 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 19962880 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 19970048 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 19979264 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 28236800 } ], "md5sum": "416f6a3d6cc85b03626155d088bd71a1" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "6751f1285cd72106f60aa9b7b6110b82" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "e889b30b0db1b4208b396725e718959a" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 7225344 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 7232512 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 11475968 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 19962880 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 19970048 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 19979264 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 28236800 } ], "md5sum": "60786c02d4469b2ffa45850152972c27" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "05f383bad66af9e7f6244015d47714e6" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "02513eabcf5e3c7df185872ffdb12728" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 7225344 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 7232512 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 11475968 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 19962880 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 19970048 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 19979264 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 28236800 } ], "md5sum": "20c600eb174aaa0c923e41d355e0c73d" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "664157c57f68babdf914ba25c45023ed" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "0beb1a0f39683ff6d3b0dc638c3de4d5" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 7225344 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 7232512 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 11475968 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 19962880 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 19970048 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 19979264 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 28236800 } ], "md5sum": "25e6ba4cb4a29fa4c2e12458f3452c80" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "77d7adf991692bed91928ec82ba76118" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "1686b572df8490d42e0564b82652827e" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 7225344 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 7232512 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 11475968 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 19962880 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 19970048 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 19979264 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 28236800 } ], "md5sum": "9109faab401725c140db08f5f2f24bee" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "2b33316f12e77665131045c97eb0e68c" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "81af6f14a38804c55112d79eec781e85" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 7225344 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 7232512 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 11475968 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 19962880 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 19970048 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 19979264 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 28236800 } ], "md5sum": "c806024caba15e2ca18ae3f169983284" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "5ae2b71f595ed38a75c3727523bcbba2" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "842efd93fac58813e357d383818a3298" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 32243712, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 7225344 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 15712256 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 15721472 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 23979008 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 25011200 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 31433728 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 32236544 } ], "md5sum": "dc09b53b68a1011a7e321da67afaa767" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "4ae2a0380be1570ae4775d2ccc38a8c7" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "92d8c5953250ccc97f479ad774caa38f" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "f734f92231c5692ad5ade3976a8f0bc0" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 25491456, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 4243456 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 12730368 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 12737536 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 12744704 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16988160 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25475072 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 25482240 } ], "md5sum": "95850aad3f8247454367ef22cf5da5f6" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "4f658fa6d95c8cc42f5cc891c296745a" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "6ed6fb8accc2ad58ba79c249084af46e" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "541583aeed483d402b784cf675273e6b" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 33526784, "records": [ { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 20765696 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 20772864 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 20780032 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 25023488 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 33510400 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 33517568 } ], "md5sum": "6517699a6017a4bb430b424fa617747f" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "86d9844ce5cd69481a2b1ab8370b49c1" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "e8ede02f01d0fef4f1f91d0794960c67" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "d712795bcccdf5fea419f733af345232" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "6fa0a6f255761e22363bbb4ee1e62673" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "0e976a9d9773ead50642c9a402d2462c" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "2122d748b08f21d1ad8fad74d9e2e2f5" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "c4cc1d40edb8514d3bfb15aa22bf70e7" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "a3d64e22d803191e89131dab7f836580" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "ec483f0d90dbd39aad704d8ab03b6d20" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "5fdcab2fb3c578b55d21dea0af2159a4" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "ad9a1f48f5769b1bf629736150d17f33" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "0d70c9a14b0ef82693413d1fe1924a97" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "240abe47a0468f34ed10c513ac7992e8" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "7435ce3c55a4a1e8da2f4e25c693e457" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "6f78e6661a86855a936f4cd0ef9a8231" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "b79215559c8481e02112f7236279a2a5" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "16230ea78968f05c629f4c02f539c5e7" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "a27bffe68189be655531c6c6d65310d3" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "79cddc04361d6708c1004a233330695d" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "742ec7b120da70a4a118215616a2cb1c" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "4c0b5bf830eb8fba0b6c1acfcd578778" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "079ac17ada092579742fd5b4c6ecc5d0" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "d792a66d96afb2b7953ca3a259d78f37" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "e315d07f59feca87b63e3b284f5d7ea5" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 16522240, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.norm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 } ], "md5sum": "6486277b39cf9301ef64d8c7666fefdc" } ] }