{ "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": "float16", "format": "f32-to-bf16", "nbytes": 603979776, "byteOffset": 0 } ], "md5sum": "501d79a3d4f0135baf65ea5edaeddfba" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "954fbf5d820fd39cf8d243f41f9dfcc3" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 21836032, "records": [ { "name": "language_model.model.layers.0.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 0 }, { "name": "language_model.model.layers.0.mlp.down_proj.weight", "shape": [ 1152, 6912 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 2304 }, { "name": "language_model.model.layers.0.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.0.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.0.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15932160 }, { "name": "language_model.model.layers.0.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15934464 }, { "name": "language_model.model.layers.0.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15934976 }, { "name": "language_model.model.layers.0.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16524800 }, { "name": "language_model.model.layers.0.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18884096 }, { "name": "language_model.model.layers.0.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18884608 }, { "name": "language_model.model.layers.0.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21243904 }, { "name": "language_model.model.layers.1.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21833728 } ], "md5sum": "1aaf988fd9a833fe811149a8711da2aa" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "022da1609f716ba2d0ad379c7c8d67f4" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.1.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.1.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.1.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.1.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.1.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.1.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.1.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.1.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.1.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.10.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "cb274154e90f6c6893aca3381909b011" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "09f66dbd2c9939cc7ff60a41147897b8" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.10.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.10.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.10.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.10.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.10.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.10.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.10.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.10.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.10.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.11.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "3635d25821340ea51e57b70fb8b1f2bc" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "a890ae8fdda9f611b489e945197a3718" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.11.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.11.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.11.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.11.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.11.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.11.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.11.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.11.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.11.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.12.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "a9b31aceec75999e2020ba13d2a55715" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "a0c047863c0535a9090420416dd0dbf3" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.12.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.12.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.12.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.12.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.12.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.12.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.12.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.12.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.12.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.13.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "3804f01db3bc3a5e053562ab1ae47fc2" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "807bd47b3301cfcce7896818347c98e3" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.13.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.13.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.13.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.13.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.13.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.13.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.13.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.13.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.13.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.14.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "a27dd06298350cfed92d7152d9a1e750" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "f4c83732ff353a20b6785f577ab62c8a" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.14.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.14.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.14.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.14.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.14.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.14.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.14.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.14.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.14.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.15.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "ebec997b7d700fb68c877fc005c7d5f6" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "2a3f0257011f0bf3780bf5de1ec6b5cf" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.15.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.15.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.15.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.15.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.15.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.15.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.15.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.15.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.15.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.16.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "c01170f88748a8f01363b8b96e3c419c" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "4e0cadaa0cfcfcf30c87939b06ddbbd0" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.16.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.16.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.16.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.16.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.16.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.16.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.16.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.16.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.16.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.17.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "57eca4e237bc892e7ec9a8108f915ca7" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "ee4412464f488e35fecc2f23c1154a70" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.17.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.17.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.17.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.17.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.17.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.17.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.17.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.17.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.17.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.18.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "8a1ed1cbba52f8cb7e0c148ad0207eb7" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "ece6c759f14f9f3d0a364bab06881aae" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.18.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.18.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.18.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.18.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.18.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.18.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.18.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.18.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.18.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.19.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "6ff044debde79e500d1ebbdf12feceda" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "29250ca793c3fe002371d97f5bcfd661" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.19.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.19.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.19.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.19.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.19.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.19.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.19.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.19.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.19.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.2.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "aae8b187b268d22520a3a604bf42520d" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "533d403ef9207477c17b502c4be325dc" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.2.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.2.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.2.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.2.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.2.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.2.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.2.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.2.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.2.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.20.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "57294316fc833afdfe31c74c78401893" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "8ac637c7d85faa50334dd8f6b1472a69" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.20.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.20.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.20.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.20.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.20.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.20.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.20.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.20.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.20.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.21.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "48d1547dc57e27f4a5b08e995d1de8fa" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "6a1cc1da21a25d8417e63f6c195cd69d" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.21.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.21.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.21.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.21.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.21.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.21.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.21.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.21.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.21.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.22.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "d24ead861a542490594db505edde98e2" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "c94a996791f0f8df325490f0a43839ee" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.22.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.22.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.22.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.22.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.22.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.22.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.22.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.22.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.22.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.23.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "5db3d5ed90a8617d4c8989bf8859cb03" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "3309afb6a15b1ec15e3b720b79c18e47" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.23.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.23.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.23.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.23.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.23.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.23.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.23.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.23.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.23.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.24.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "3e4696a53aaa5b2f25374dd1927920ca" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "abd8f15975a5b2d2e8eb3fc041b052e3" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.24.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.24.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.24.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.24.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.24.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.24.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.24.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.24.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.24.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.25.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "eee45006eb0ef0123a48f28885cd0c12" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "1cb79ebe6bc442a760efb8915b3069c9" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.25.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.25.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.25.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.25.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.25.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.25.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.25.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.25.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.25.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.3.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "3b684809bf88ba5e766a172f0b673375" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "6cd986e6f35bd057f813517d9ef7ea43" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.3.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.3.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.3.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.3.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.3.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.3.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.3.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.3.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.3.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.4.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "bbb01844761f2518972f1ea1a36c2e79" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "3eda42f2a2371b9ab3e1e25d2b37f7b1" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.4.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.4.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.4.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.4.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.4.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.4.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.4.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.4.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.4.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.5.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "375c914f3bb9aeb576dc7843e62e6982" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "e09c61e02c446e7ffb44d27e333b0c8c" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.5.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.5.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.5.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.5.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.5.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.5.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.5.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.5.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.5.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.6.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "5b2f3a8b5531fc3e776fdf00bc2e0410" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "0651b281fe7e218aef7815f7f11c4cbb" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.6.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.6.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.6.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.6.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.6.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.6.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.6.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.6.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.6.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.7.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "92ec62d1db25e25d97a11151cfd4e6db" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "b56156d41f96f00b84603b3be406c9b9" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.7.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.7.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.7.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.7.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.7.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.7.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.7.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.7.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.7.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.8.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "ff663c724032e5f9c700f1242df1a4f5" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "7759839b7c75c18953f60eeaad4cd3ef" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.8.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.8.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.8.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.8.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.8.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.8.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.8.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.8.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.8.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.layers.9.input_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "eaaa0dd73bb0467b9b0846bf9b436ca6" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 31850496, "byteOffset": 0 } ], "md5sum": "d71df9576ffe9eeadaf638ef21981f0f" }, { "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": "float16", "format": "f32-to-bf16", "nbytes": 15925248, "byteOffset": 0 }, { "name": "language_model.model.layers.9.post_attention_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15925248 }, { "name": "language_model.model.layers.9.post_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15927552 }, { "name": "language_model.model.layers.9.pre_feedforward_layernorm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 15929856 }, { "name": "language_model.model.layers.9.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 15932160 }, { "name": "language_model.model.layers.9.self_attn.k_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 15932672 }, { "name": "language_model.model.layers.9.self_attn.o_proj.weight", "shape": [ 1152, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 16522496 }, { "name": "language_model.model.layers.9.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 512, "byteOffset": 18881792 }, { "name": "language_model.model.layers.9.self_attn.q_proj.weight", "shape": [ 1024, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2359296, "byteOffset": 18882304 }, { "name": "language_model.model.layers.9.self_attn.v_proj.weight", "shape": [ 256, 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 589824, "byteOffset": 21241600 }, { "name": "language_model.model.norm.weight", "shape": [ 1152 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 21831424 } ], "md5sum": "24d5a4265c59a6a95a239e6fa5a70ff7" } ] }