{ "metadata": { "ParamSize": 218, "ParamBytes": 1072392704.0, "BitsPerParam": 32.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 671088640, "records": [ { "name": "language_model.model.embed_tokens.weight", "shape": [ 262144, 640 ], "dtype": "float32", "format": "raw", "nbytes": 671088640, "byteOffset": 0 } ], "md5sum": "dc61b2dbde6b034d5b7726300ba2bbe6" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 27539968, "records": [ { "name": "language_model.model.layers.0.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 0 }, { "name": "language_model.model.layers.0.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 2560 }, { "name": "language_model.model.layers.0.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 5245440 }, { "name": "language_model.model.layers.0.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 15731200 }, { "name": "language_model.model.layers.0.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 15733760 }, { "name": "language_model.model.layers.0.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 15736320 }, { "name": "language_model.model.layers.0.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 15738880 }, { "name": "language_model.model.layers.0.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 15739904 }, { "name": "language_model.model.layers.0.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 16395264 }, { "name": "language_model.model.layers.0.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 19016704 }, { "name": "language_model.model.layers.0.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 19017728 }, { "name": "language_model.model.layers.0.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 21639168 }, { "name": "language_model.model.layers.1.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 22294528 }, { "name": "language_model.model.layers.1.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 22297088 } ], "md5sum": "db92957e5f38ac46b880e648819040dd" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 33444352, "records": [ { "name": "language_model.model.layers.1.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 0 }, { "name": "language_model.model.layers.1.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10485760 }, { "name": "language_model.model.layers.1.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10488320 }, { "name": "language_model.model.layers.1.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10490880 }, { "name": "language_model.model.layers.1.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 10493440 }, { "name": "language_model.model.layers.1.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 10494464 }, { "name": "language_model.model.layers.1.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 11149824 }, { "name": "language_model.model.layers.1.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 13771264 }, { "name": "language_model.model.layers.1.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 13772288 }, { "name": "language_model.model.layers.1.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 16393728 }, { "name": "language_model.model.layers.10.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 17049088 }, { "name": "language_model.model.layers.10.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 17051648 }, { "name": "language_model.model.layers.10.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 22294528 }, { "name": "language_model.model.layers.10.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32780288 }, { "name": "language_model.model.layers.10.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32782848 }, { "name": "language_model.model.layers.10.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32785408 }, { "name": "language_model.model.layers.10.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 32787968 }, { "name": "language_model.model.layers.10.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 32788992 } ], "md5sum": "f0cdda6253df27411398b7f2ca55c20d" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 33439232, "records": [ { "name": "language_model.model.layers.10.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 0 }, { "name": "language_model.model.layers.10.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 2621440 }, { "name": "language_model.model.layers.10.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 2622464 }, { "name": "language_model.model.layers.10.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 5243904 }, { "name": "language_model.model.layers.11.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 5899264 }, { "name": "language_model.model.layers.11.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 5901824 }, { "name": "language_model.model.layers.11.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 11144704 }, { "name": "language_model.model.layers.11.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21630464 }, { "name": "language_model.model.layers.11.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21633024 }, { "name": "language_model.model.layers.11.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21635584 }, { "name": "language_model.model.layers.11.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 21638144 }, { "name": "language_model.model.layers.11.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 21639168 }, { "name": "language_model.model.layers.11.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 22294528 }, { "name": "language_model.model.layers.11.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 24915968 }, { "name": "language_model.model.layers.11.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 24916992 }, { "name": "language_model.model.layers.11.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 27538432 }, { "name": "language_model.model.layers.12.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 28193792 }, { "name": "language_model.model.layers.12.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 28196352 } ], "md5sum": "67d8105d19337ff42c9f7a9e9adf70e7" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33444352, "records": [ { "name": "language_model.model.layers.12.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 0 }, { "name": "language_model.model.layers.12.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10485760 }, { "name": "language_model.model.layers.12.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10488320 }, { "name": "language_model.model.layers.12.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10490880 }, { "name": "language_model.model.layers.12.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 10493440 }, { "name": "language_model.model.layers.12.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 10494464 }, { "name": "language_model.model.layers.12.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 11149824 }, { "name": "language_model.model.layers.12.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 13771264 }, { "name": "language_model.model.layers.12.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 13772288 }, { "name": "language_model.model.layers.12.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 16393728 }, { "name": "language_model.model.layers.13.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 17049088 }, { "name": "language_model.model.layers.13.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 17051648 }, { "name": "language_model.model.layers.13.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 22294528 }, { "name": "language_model.model.layers.13.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32780288 }, { "name": "language_model.model.layers.13.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32782848 }, { "name": "language_model.model.layers.13.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32785408 }, { "name": "language_model.model.layers.13.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 32787968 }, { "name": "language_model.model.layers.13.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 32788992 } ], "md5sum": "9f91b5b1350459df2806657d22f0a095" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 33439232, "records": [ { "name": "language_model.model.layers.13.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 0 }, { "name": "language_model.model.layers.13.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 2621440 }, { "name": "language_model.model.layers.13.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 2622464 }, { "name": "language_model.model.layers.13.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 5243904 }, { "name": "language_model.model.layers.14.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 5899264 }, { "name": "language_model.model.layers.14.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 5901824 }, { "name": "language_model.model.layers.14.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 11144704 }, { "name": "language_model.model.layers.14.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21630464 }, { "name": "language_model.model.layers.14.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21633024 }, { "name": "language_model.model.layers.14.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21635584 }, { "name": "language_model.model.layers.14.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 21638144 }, { "name": "language_model.model.layers.14.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 21639168 }, { "name": "language_model.model.layers.14.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 22294528 }, { "name": "language_model.model.layers.14.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 24915968 }, { "name": "language_model.model.layers.14.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 24916992 }, { "name": "language_model.model.layers.14.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 27538432 }, { "name": "language_model.model.layers.15.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 28193792 }, { "name": "language_model.model.layers.15.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 28196352 } ], "md5sum": "4d98f933fdbb71c2eaa1ec154cccfe69" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33444352, "records": [ { "name": "language_model.model.layers.15.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 0 }, { "name": "language_model.model.layers.15.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10485760 }, { "name": "language_model.model.layers.15.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10488320 }, { "name": "language_model.model.layers.15.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10490880 }, { "name": "language_model.model.layers.15.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 10493440 }, { "name": "language_model.model.layers.15.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 10494464 }, { "name": "language_model.model.layers.15.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 11149824 }, { "name": "language_model.model.layers.15.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 13771264 }, { "name": "language_model.model.layers.15.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 13772288 }, { "name": "language_model.model.layers.15.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 16393728 }, { "name": "language_model.model.layers.16.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 17049088 }, { "name": "language_model.model.layers.16.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 17051648 }, { "name": "language_model.model.layers.16.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 22294528 }, { "name": "language_model.model.layers.16.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32780288 }, { "name": "language_model.model.layers.16.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32782848 }, { "name": "language_model.model.layers.16.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32785408 }, { "name": "language_model.model.layers.16.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 32787968 }, { "name": "language_model.model.layers.16.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 32788992 } ], "md5sum": "a8c240e5a94b1661f5d04c233906c104" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 33439232, "records": [ { "name": "language_model.model.layers.16.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 0 }, { "name": "language_model.model.layers.16.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 2621440 }, { "name": "language_model.model.layers.16.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 2622464 }, { "name": "language_model.model.layers.16.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 5243904 }, { "name": "language_model.model.layers.17.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 5899264 }, { "name": "language_model.model.layers.17.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 5901824 }, { "name": "language_model.model.layers.17.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 11144704 }, { "name": "language_model.model.layers.17.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21630464 }, { "name": "language_model.model.layers.17.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21633024 }, { "name": "language_model.model.layers.17.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21635584 }, { "name": "language_model.model.layers.17.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 21638144 }, { "name": "language_model.model.layers.17.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 21639168 }, { "name": "language_model.model.layers.17.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 22294528 }, { "name": "language_model.model.layers.17.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 24915968 }, { "name": "language_model.model.layers.17.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 24916992 }, { "name": "language_model.model.layers.17.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 27538432 }, { "name": "language_model.model.layers.2.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 28193792 }, { "name": "language_model.model.layers.2.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 28196352 } ], "md5sum": "7c520ba0ed2bcd55481a4cc76a4ccc19" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 33444352, "records": [ { "name": "language_model.model.layers.2.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 0 }, { "name": "language_model.model.layers.2.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10485760 }, { "name": "language_model.model.layers.2.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10488320 }, { "name": "language_model.model.layers.2.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10490880 }, { "name": "language_model.model.layers.2.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 10493440 }, { "name": "language_model.model.layers.2.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 10494464 }, { "name": "language_model.model.layers.2.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 11149824 }, { "name": "language_model.model.layers.2.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 13771264 }, { "name": "language_model.model.layers.2.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 13772288 }, { "name": "language_model.model.layers.2.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 16393728 }, { "name": "language_model.model.layers.3.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 17049088 }, { "name": "language_model.model.layers.3.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 17051648 }, { "name": "language_model.model.layers.3.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 22294528 }, { "name": "language_model.model.layers.3.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32780288 }, { "name": "language_model.model.layers.3.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32782848 }, { "name": "language_model.model.layers.3.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32785408 }, { "name": "language_model.model.layers.3.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 32787968 }, { "name": "language_model.model.layers.3.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 32788992 } ], "md5sum": "bc07cc11ff8fc6a08c61013350bc81b0" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33439232, "records": [ { "name": "language_model.model.layers.3.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 0 }, { "name": "language_model.model.layers.3.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 2621440 }, { "name": "language_model.model.layers.3.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 2622464 }, { "name": "language_model.model.layers.3.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 5243904 }, { "name": "language_model.model.layers.4.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 5899264 }, { "name": "language_model.model.layers.4.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 5901824 }, { "name": "language_model.model.layers.4.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 11144704 }, { "name": "language_model.model.layers.4.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21630464 }, { "name": "language_model.model.layers.4.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21633024 }, { "name": "language_model.model.layers.4.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21635584 }, { "name": "language_model.model.layers.4.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 21638144 }, { "name": "language_model.model.layers.4.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 21639168 }, { "name": "language_model.model.layers.4.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 22294528 }, { "name": "language_model.model.layers.4.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 24915968 }, { "name": "language_model.model.layers.4.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 24916992 }, { "name": "language_model.model.layers.4.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 27538432 }, { "name": "language_model.model.layers.5.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 28193792 }, { "name": "language_model.model.layers.5.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 28196352 } ], "md5sum": "45c4d9bc7408e84a08965b347046617b" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33444352, "records": [ { "name": "language_model.model.layers.5.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 0 }, { "name": "language_model.model.layers.5.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10485760 }, { "name": "language_model.model.layers.5.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10488320 }, { "name": "language_model.model.layers.5.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10490880 }, { "name": "language_model.model.layers.5.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 10493440 }, { "name": "language_model.model.layers.5.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 10494464 }, { "name": "language_model.model.layers.5.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 11149824 }, { "name": "language_model.model.layers.5.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 13771264 }, { "name": "language_model.model.layers.5.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 13772288 }, { "name": "language_model.model.layers.5.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 16393728 }, { "name": "language_model.model.layers.6.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 17049088 }, { "name": "language_model.model.layers.6.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 17051648 }, { "name": "language_model.model.layers.6.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 22294528 }, { "name": "language_model.model.layers.6.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32780288 }, { "name": "language_model.model.layers.6.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32782848 }, { "name": "language_model.model.layers.6.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32785408 }, { "name": "language_model.model.layers.6.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 32787968 }, { "name": "language_model.model.layers.6.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 32788992 } ], "md5sum": "6615fb022c3490908b0f43d89fa441cf" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 33439232, "records": [ { "name": "language_model.model.layers.6.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 0 }, { "name": "language_model.model.layers.6.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 2621440 }, { "name": "language_model.model.layers.6.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 2622464 }, { "name": "language_model.model.layers.6.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 5243904 }, { "name": "language_model.model.layers.7.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 5899264 }, { "name": "language_model.model.layers.7.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 5901824 }, { "name": "language_model.model.layers.7.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 11144704 }, { "name": "language_model.model.layers.7.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21630464 }, { "name": "language_model.model.layers.7.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21633024 }, { "name": "language_model.model.layers.7.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 21635584 }, { "name": "language_model.model.layers.7.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 21638144 }, { "name": "language_model.model.layers.7.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 21639168 }, { "name": "language_model.model.layers.7.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 22294528 }, { "name": "language_model.model.layers.7.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 24915968 }, { "name": "language_model.model.layers.7.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 24916992 }, { "name": "language_model.model.layers.7.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 27538432 }, { "name": "language_model.model.layers.8.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 28193792 }, { "name": "language_model.model.layers.8.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 28196352 } ], "md5sum": "e9b74bc9c8eafd7dd1ce4be73f0d68c5" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 33444352, "records": [ { "name": "language_model.model.layers.8.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 0 }, { "name": "language_model.model.layers.8.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10485760 }, { "name": "language_model.model.layers.8.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10488320 }, { "name": "language_model.model.layers.8.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 10490880 }, { "name": "language_model.model.layers.8.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 10493440 }, { "name": "language_model.model.layers.8.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 10494464 }, { "name": "language_model.model.layers.8.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 11149824 }, { "name": "language_model.model.layers.8.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 13771264 }, { "name": "language_model.model.layers.8.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 13772288 }, { "name": "language_model.model.layers.8.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 16393728 }, { "name": "language_model.model.layers.9.input_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 17049088 }, { "name": "language_model.model.layers.9.mlp.down_proj.weight", "shape": [ 640, 2048 ], "dtype": "float32", "format": "raw", "nbytes": 5242880, "byteOffset": 17051648 }, { "name": "language_model.model.layers.9.mlp.gate_up_proj.weight", "shape": [ 4096, 640 ], "dtype": "float32", "format": "raw", "nbytes": 10485760, "byteOffset": 22294528 }, { "name": "language_model.model.layers.9.post_attention_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32780288 }, { "name": "language_model.model.layers.9.post_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32782848 }, { "name": "language_model.model.layers.9.pre_feedforward_layernorm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 32785408 }, { "name": "language_model.model.layers.9.self_attn.k_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 32787968 }, { "name": "language_model.model.layers.9.self_attn.k_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 32788992 } ], "md5sum": "b50e8fd4079ebda7619cf73c0d544ccb" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 5901824, "records": [ { "name": "language_model.model.layers.9.self_attn.o_proj.weight", "shape": [ 640, 1024 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 0 }, { "name": "language_model.model.layers.9.self_attn.q_norm.weight", "shape": [ 256 ], "dtype": "float32", "format": "raw", "nbytes": 1024, "byteOffset": 2621440 }, { "name": "language_model.model.layers.9.self_attn.q_proj.weight", "shape": [ 1024, 640 ], "dtype": "float32", "format": "raw", "nbytes": 2621440, "byteOffset": 2622464 }, { "name": "language_model.model.layers.9.self_attn.v_proj.weight", "shape": [ 256, 640 ], "dtype": "float32", "format": "raw", "nbytes": 655360, "byteOffset": 5243904 }, { "name": "language_model.model.norm.weight", "shape": [ 640 ], "dtype": "float32", "format": "raw", "nbytes": 2560, "byteOffset": 5899264 } ], "md5sum": "5a23d75cafcf542f60af43a71f00fa3f" } ] }