{ "metadata": { "ParamSize": 314, "ParamBytes": 1999771904.0, "BitsPerParam": 16.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 603979776, "records": [ { "name": "language_model.model.embed_tokens.weight", "shape": [ 262144, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 603979776, "byteOffset": 0 } ], "md5sum": "a63af4bbe5f455aa945f4dd02fc39efc" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.0.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "af4874a1860fd1d9824140f92f76568b" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 21836032, "records": [ { "name": "language_model.model.layers.0.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 0 }, { "name": "language_model.model.layers.0.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 2304 }, { "name": "language_model.model.layers.0.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.0.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.0.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15932160 }, { "name": "language_model.model.layers.0.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15934464 }, { "name": "language_model.model.layers.0.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15934976 }, { "name": "language_model.model.layers.0.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16524800 }, { "name": "language_model.model.layers.0.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18884096 }, { "name": "language_model.model.layers.0.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18884608 }, { "name": "language_model.model.layers.0.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21243904 }, { "name": "language_model.model.layers.1.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21833728 } ], "md5sum": "ea50a2bf3c71b964c7c0c8213a6b2b4c" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.1.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "672403991efba2896309444263ab6018" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.1.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.1.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.1.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.1.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.1.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.1.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.1.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.1.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.1.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.1.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.10.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "87f1502a86bb879c688d0a4392ac87f9" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.10.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "2f99bc497c92dbb471362f0e6238a1f7" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.10.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.10.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.10.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.10.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.10.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.10.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.10.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.10.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.10.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.10.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.11.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "8013fc5f3f1d4cad952eae0c213b7ee5" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.11.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "d1c3e73b037ae4189904b7d097a4b626" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.11.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.11.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.11.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.11.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.11.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.11.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.11.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.11.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.11.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.11.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.12.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "788b90c97e2225c0e2053bab7020b948" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.12.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "d2dd83c7f3023e1b2c6ba0cbf9d995e8" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.12.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.12.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.12.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.12.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.12.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.12.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.12.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.12.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.12.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.12.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.13.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "690cccc27c92dc254f40e2ab07056dea" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.13.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "001432cb9c5c9f8a5ad1c24cbfc1d52e" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.13.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.13.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.13.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.13.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.13.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.13.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.13.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.13.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.13.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.13.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.14.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "370d92980d178487e3e175e71bb53c90" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.14.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "8015aeaeef76588defdf9d119146212d" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.14.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.14.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.14.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.14.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.14.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.14.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.14.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.14.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.14.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.14.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.15.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "b6e812a0f5965cc97d6b395120973fb2" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.15.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "cf44806da653ac9f2321decfcb166ad7" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.15.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.15.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.15.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.15.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.15.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.15.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.15.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.15.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.15.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.15.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.16.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "b6ef998485911c1130cb3ad247ac6009" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.16.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "b95ac585b28e07ee38cafbf9a77ea47d" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.16.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.16.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.16.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.16.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.16.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.16.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.16.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.16.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.16.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.16.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.17.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "2ee14e1c7261d193a069812199b1e2fe" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.17.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "6089b21b8643de7e9599e4c3098926c0" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.17.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.17.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.17.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.17.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.17.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.17.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.17.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.17.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.17.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.17.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.18.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "a65807e48b954198fd559e1c270fc85d" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.18.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "f93f7d7a8cf255a4cc1d5ebc0537afed" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.18.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.18.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.18.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.18.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.18.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.18.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.18.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.18.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.18.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.18.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.19.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "035ad93f2ec148525168c150e769d468" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.19.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "987f8dab641ddfb703f6cc2a2dfc87d3" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.19.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.19.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.19.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.19.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.19.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.19.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.19.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.19.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.19.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.19.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.2.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "4cff1d3490267bc155ac4fc951bf0f74" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.2.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "9feb69f4e141c09b85b0ccb80eef9a04" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.2.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.2.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.2.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.2.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.2.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.2.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.2.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.2.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.2.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.2.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.20.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "66d9f8134f761532eb0341452fb2a7a1" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.20.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "666e8cdc3a7f8090039e11d5942f19d1" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.20.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.20.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.20.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.20.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.20.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.20.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.20.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.20.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.20.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.20.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.21.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "cc58172d4f5c144faa41da4d3099ca23" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.21.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "626877e0b23555f18fffad1d1d778263" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.21.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.21.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.21.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.21.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.21.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.21.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.21.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.21.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.21.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.21.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.22.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "cdc2e085905dff4274c7eb02c658f27e" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.22.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "5eb6efa86dcfe2b1753a997b90f8ce41" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.22.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.22.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.22.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.22.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.22.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.22.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.22.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.22.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.22.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.22.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.23.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "67ae00a27bc88a31e8d3e65955f684ca" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.23.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "c04dc26a947fdbfea0fa8f9a5de98df0" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.23.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.23.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.23.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.23.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.23.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.23.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.23.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.23.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.23.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.23.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.24.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "c85b2f6ae839f40733188009661f40d2" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.24.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "f48b2ac5a07ca2560ed7eaf207bb917e" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.24.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.24.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.24.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.24.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.24.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.24.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.24.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.24.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.24.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.24.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.25.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "7511996b5c2a2f5926a916731a51968a" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.25.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "f0101cc2348bc3fa6d77125b83b5d780" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.25.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.25.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.25.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.25.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.25.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.25.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.25.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.25.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.25.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.25.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.3.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "0961c67d790c41e39222a8068a4e179d" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.3.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "3dc19bfb1858c0edcb9491f907276b5a" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.3.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.3.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.3.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.3.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.3.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.3.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.3.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.3.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.3.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.3.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.4.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "2896017bc3b47e0894b70ec0fa1846b5" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.4.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "94677b923988f60ba57e65090c6496d5" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.4.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.4.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.4.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.4.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.4.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.4.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.4.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.4.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.4.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.4.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.5.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "a358287eb382dc23b4d2604e4dcb1c0c" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.5.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "11199ec7ca88c8c1bc4513f986c84285" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.5.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.5.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.5.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.5.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.5.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.5.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.5.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.5.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.5.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.5.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.6.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "92b7715b69796fd5c2fdc69d6a29c8a3" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.6.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "b8ae3b703635a63b6262e9c000927e08" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.6.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.6.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.6.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.6.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.6.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.6.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.6.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.6.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.6.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.6.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.7.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "51fd8095d6ba995de964cea3ddfada38" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.7.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "2ab7a9acebda88ebb604b7e256a645b6" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.7.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.7.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.7.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.7.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.7.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.7.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.7.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.7.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.7.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.7.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.8.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "1c9ebe4c8fc1d47ffcd1248aee2f9291" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.8.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "185b5ccdc6fddc724d993c173e707078" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.8.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.8.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.8.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.8.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.8.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.8.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.8.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.8.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.8.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.8.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.9.input_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "8ecd51e4022fa8a7811f570ee7381381" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 31850496, "records": [ { "name": "language_model.model.layers.9.mlp.gate_up_proj.weight", "shape": [ 13824, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "f6cf6aa9800735866a14bcdc62f121c5" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 21833728, "records": [ { "name": "language_model.model.layers.9.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.9.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.9.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.9.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.9.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.9.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.9.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.9.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.9.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.9.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.norm.weight", "shape": [ 1152 ], "dtype": "bfloat16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "b7339c68b8dbcaaf29ead73018c66553" } ] }