{ "metadata": { "ParamSize": 485, "ParamBytes": 9231626240.0, "BitsPerParam": 2.992706525598843 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 388956160, "records": [ { "name": "lm_head.q_weight", "shape": [ 151936, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 388956160, "byteOffset": 0 } ], "md5sum": "69cdf0f57245698e5c90885411b0ec52" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 48619520, "records": [ { "name": "lm_head.q_scale", "shape": [ 151936, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 48619520, "byteOffset": 0 } ], "md5sum": "e95a4f4efa8704f957b40e2ba1af98b0" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "4db16b1093f76b47ac70c129a9aa7c25" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "9b69e52121bcd0c1a1ae5fa834ff295f" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 388956160, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 388956160, "byteOffset": 0 } ], "md5sum": "10756f4c42da15eecbab1ecca581c2bc" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 48619520, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 48619520, "byteOffset": 0 } ], "md5sum": "504b727ff61d0adbc88a7bd7578a3d0b" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "edaa91d53a3c91c598f7c9e24375dc37" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "9faab8671be2865ad468c761570fd97a" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "9e42f265965b32d0bcfaccae393d823c" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33474816, "records": [ { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 0 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 10240 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 5580800 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16721920 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16732160 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16742400 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 16752640 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 22323200 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 33464320 }, { "name": "model.layers.0.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 33474560 } ], "md5sum": "151f40151a37045a9271f9c4c33a2ee1" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "0c795fbe57f1f2c49aa6f10174ba3392" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "6963d79539d3d2089e051cdd9eb1e5ec" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.0.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "a85aa522d016c18b933e84faee9cd1ab" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.1.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "5aee4e6ac6cb32e3fde9024385127e88" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "da367152309e112a40f7e5989b2ea56e" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "ad5a7598710ca5265d5b9b4929e139b0" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "6e0819abb3136d59397478cf49c31bb7" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.1.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.2.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "ab26e3b6860d4b73207e4fa2272337d2" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "fbc923e8a795a307f98202039cadeef4" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2e6dcec3d4413e5af1e846bbce191986" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 30474752, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.2.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 17039616 }, { "name": "model.layers.3.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 28180736 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28180992 } ], "md5sum": "7a8aeb1767c8c63e1bc4aa0fe1f7ab57" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "d70d33550c40b8688835a7cfe78c694c" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "9ec390525a2b44f5ac396fcd34702b8a" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "b14c47c03fc6e67ead76ad783e28666b" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.3.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.10.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "3501fc97374ce72f6cab5eb8ec8bb9ff" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "310bb690a360dd25b94781bbdef15cea" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "17a3e621b3977816c3a8948a8abcc0e5" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.10.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "5c9181be2bdd620c9d0a49f760d8a58e" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.11.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "a687a9800e36dd06805b41350befdba5" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "0335d9382109898e6d5adbee785268f4" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "232dfb24bf07fcbadabd2692608cb629" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7f155d3c44c3a636dd2620e6498e291c" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.11.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.12.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "33106983872888e82c9d36afafde5b4c" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "89d26cedf1628caff23cfcf8b0b44199" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "3af372385f32fa1dd270377e514921c9" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.12.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "1da34b72e9598a27b1cb17267df6f7b2" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.13.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "19a0820f8baade045c2642cbb3669bf9" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "3363a7eeb6c33037ceb1b29dc8ac1fce" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "eb6153a0eb4983143c5ccc74d024cf8b" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7f5c561730b0c21fbacb80b25978000e" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.13.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.14.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "06265bbc838a7ebf6c621da33ca4a48e" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "652efe023051dc3a1480d05f77c1f53d" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "0b56f61ba0b74a99c50df330b5f19c7d" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 30474752, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.14.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 17039616 }, { "name": "model.layers.15.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 28180736 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28180992 } ], "md5sum": "6ebc22516f50ea24b2bc7f646effcee0" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "4e9a54fe1016d86a8772ef544d8a6819" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "576c75bfb8e94c01f3d385c44f638567" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "71e1697053a2a25403af27834fe0ee7a" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 31488256, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.15.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31478016 } ], "md5sum": "f2bda8a5b34a988db37d2b56c2ccb4aa" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "f5a2235239df75921d6194550e20ea9c" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "849e1afb344d8a56275b5688c76c2cbe" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "451351039eda3a311e22d508a28d2a96" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 24606976, "records": [ { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 0 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 5570560 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 5580800 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 5591040 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 11161600 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22302720 }, { "name": "model.layers.16.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22312960 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 22313216 } ], "md5sum": "c46d92c6e416dad38993e473236b1e5c" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "6a87129dec344788325ce06bef4b7546" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "d5f0baafc6ecfd819310635529169d90" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "b44b7ac8485e818012a36878b8760917" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.16.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.17.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "68a5509df8c1842541c4c85f2e339ba8" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "a3974d8ff6b819cb8fca247ecf66cffd" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "2389f6c9980ccb0edb1a2a671fcf1ecd" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.17.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "934701bc57f5d34c710f7b9011251b3e" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.18.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "a0d1b4bc0507c6984d5166bc34865e71" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "4aab37ce96cfce413baaeb52b6dd1667" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "41ca307a3003552c37a25ccb6445d36c" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "221fce9a4e6bbb25ea27231d2d2e5ede" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.18.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.19.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "899020d911df0b9ef2a380796c276860" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "ef35f72e86d7331f287642683d15f957" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "c130f5315bb68969a66de38c7b58268f" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.19.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "15404b0b2054068ab6072258a2f5e493" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.20.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "b5782c114dcc0d1c53e8eb3642d1f9e4" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "94491e1db5e40c2cb30fb555aaaa685a" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "44e40ccfe4f90217c75b6d514dbeca51" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 28180992, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.20.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 14745856 }, { "name": "model.layers.21.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 25886976 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 25887232 } ], "md5sum": "1125cb42c0b6dbc3e8b962760c2ca7c9" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "010537e2ff96467411906cac08ec5057" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "6239766eec00cd2d8007316e8422be8d" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "d8386b28a350dd0fa783d3021b3c41a1" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 25917696, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.21.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20326656 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20336896 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 20347136 } ], "md5sum": "767c01b8cf18baab4b065498e5c16f91" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.22.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "5e8838623bd7b37dcf8451c7512d0fc4" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "fea6f389aad0042fdf08a35de8648385" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "988514ec6add8323d3813ce17334fdcd" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "720f50d1d6ce4a0dea3bb5cab6a80dd0" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.22.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.23.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "30d74a638a39ae38583d15fc0618580c" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "bf897bc2827de006b57cede06525902c" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "8d872ba89f9eabd7a75ae5c4006f5c06" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.23.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "7b95bdeafac78184149d20be7a36c292" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.24.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "ba575fbccfac5a1fcae2b273ecf9962e" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "b35e8c80cda8f1f6cb99f3478558ee0e" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "8f354cf257f17511eb4b0c7735e46f1e" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "fae7cc18cc90199886c1ee436ba0dc21" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.24.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.25.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "bf33ee401bb3541e557a8cf12fc1acbd" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "59dd69d23d76a63a019341e63f4942a5" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "e5f458a328f04401af964f52dce26bce" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.25.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "f3ff1a47ac554c8724cd7a721639b823" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.26.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "bbdf013d0422571f9f710bd073b2a72a" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "0cca521eee365d00a421493c687fbc47" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c654aaafcc46d028cfb143918afc2687" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 28180992, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.26.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 14745856 }, { "name": "model.layers.27.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 25886976 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 25887232 } ], "md5sum": "0c17951d18d8b1eeefac89f928ff7100" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "4fa456e1412abacb7f889883c988a1b4" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "2de2e6dc1ea0182d1652e87a98a65f64" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "6bc5546ebf72aaf25327500020b5c740" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 25917696, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.27.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20326656 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20336896 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 20347136 } ], "md5sum": "09d0170a8fe1dd4b821684d3e6b16f50" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.28.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "194862b890b9959a51ff04186950cce5" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "16d66ec0c4512fbbbc54d9952575ac90" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "73940ac4d9e0d88b04ce2c6f735c4b58" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "738c6b75d5953422ad5e26d6bacaf27e" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.28.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.29.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "0547707c638038b71b78cf1094eec6e1" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "5e803305f3fe6562f654fe2db51f00ad" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "67d8fcfc34531b3ee232ef22a155de6b" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.29.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "d18dca73fb54495fedc36c2093c0a2ae" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.30.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "cc741b03b29ecdcc2440e91394b61913" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "cad90cec97c7518a8b1a9cdcd5fd5638" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "d5b753e8b79fcd8eb442808a22c09fd6" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "1ab82138bf33c0a1bb3ceb8053f5f8c1" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.30.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.31.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "0812f0546e440f7e5d536a4b1551f5a4" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "d13bd96106a6dfad62d4aad3825ac55e" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "764e0402f8a31ef98966650e2e978524" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.31.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "3c7e9fae50ae9fc60658c018aa7a2692" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.32.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "294355c1ead59261a521ee6566a6b0bd" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "55511aaa4e31e7ae0bfd7009c3bbb1b0" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "100e5b7d5ce0674d2f1fb4287252776f" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 28180992, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.32.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 14745856 }, { "name": "model.layers.33.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 25886976 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 25887232 } ], "md5sum": "a9b3fab5abe3e9dc726fa96568a90179" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "1f808d3a804533eada105fabac8381f8" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "9bbd7e8bdf2173a723203400d03b5f1b" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "dcb00d7c19c18fda7a680b1d2f36dcf7" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 25917696, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.33.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20326656 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20336896 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 20347136 } ], "md5sum": "c9783f8155d1b0cf7ddd2405a729c490" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.4.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "f872c7ad24126e52ec031c130472592b" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "5b8378321225b7a829acca9a1c1cde2b" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "56c97922ca6a55befd220f8635672ab4" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "34082102d26f16851345f2690b336f56" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.4.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.5.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "1ef1b870d9330f4fae172e440d86083b" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "5739a6fa6409b07f661e64f7024ca83d" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "7aa5fd9a0a19ec786767890b5ff68c52" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.5.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "723092a77c9e5c811bc9070a068f53ab" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.6.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "1c2d80bdc8e0a0862108da6ee61581d8" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "8f3c6fc168552be2057f588bb1aaeef7" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "32444a4c5dfa27292586b183fa859770" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "74e68c93e0465693c4c0a8da26d1840d" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.6.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.7.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "75b5376169d8960b4a360d4a285705e7" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "cfdf1a5dfc9ded60c25f445fc6c39f1f" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "0e6a656ec1a95d55d7c45b6f307eb8c8" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.7.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "419d7e2ed7ec2b6820062c08be097f6f" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.8.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "3784d604f3f8ab16c8ade12314468d0a" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 33096192, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.8.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.9.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745856 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 14746112 } ], "md5sum": "a2e7fdb5662fd297624b40a26e71efad" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "675f1e133cf8762b6b391643ab1d7e28" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "31294cb468319dbde0bd013693422252" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "e1ddfbdeebf859daf87a75368ba8cc37" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 28211456, "records": [ { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.9.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22620416 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22630656 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 22640896 } ], "md5sum": "33d2e1e57a8d0f7653dbf207493f2b32" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.34.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "dae4624602afde46d3e9986655d74488" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "4e8d04f0658f2791adef8f8eaf9d5e95" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "d278568ec71debcb94a4d2e7078ac3bd" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "25b52103a22b0020980ae050f01aa0c0" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.34.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.35.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "fbbf3939df648d85a0e96780169aa388" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "d4719f8795cf4bb200e66481a78a623f" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "8a146643f0954e37598dba06248d86f3" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.35.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "4d8c466e4992e73b355c6941fc846871" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.36.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.36.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "0cf899f6ec6b7949076e0f71a0c6915d" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "93c834b56f5a71e611e4c10ad0675a71" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "347fd2d31ed675b68b3ec7c4ba29199c" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.37.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "fe14eb3497143cdb7cd0a3961792e175" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 31478272, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.36.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745856 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 14756096 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 20326656 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 31467776 }, { "name": "model.layers.37.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 31478016 } ], "md5sum": "ad798b5e0131f35b445210c738f1ca0e" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 44564480, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 5120, 2176 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 44564480, "byteOffset": 0 } ], "md5sum": "a5163bfbe3178a405acbe0955aff3ba6" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 89128960, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 34816, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 89128960, "byteOffset": 0 } ], "md5sum": "11a3819ea0e58c9c6680b9d82109bc5f" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 22620416, "records": [ { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.37.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039616 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 5120, 544 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 5570560, "byteOffset": 17049856 } ], "md5sum": "9b255d6f90f0e03fa0d6790b5caa0190" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 31795456, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 34816, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 11141120, "byteOffset": 0 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11141120 }, { "name": "model.layers.38.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 11151360 }, { "name": "model.layers.38.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 11151616 }, { "name": "model.layers.38.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 29501696 } ], "md5sum": "78196ff4c3722bffcf0d025335f53768" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 33096192, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.38.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745600 }, { "name": "model.layers.39.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 14745856 }, { "name": "model.layers.39.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 14746112 } ], "md5sum": "771b86837599e5e468687234c7ecaa85" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 17039616, "records": [ { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.39.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 17039360 } ], "md5sum": "785e76fa2fc59e4a73f7a3f034b3f13e" } ] }