diff --git a/config.json b/config.json new file mode 100644 index 0000000..94fa79c --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "UCLAML/Llama-3-Instruct-8B-SPPO-Iter2-bf", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.33.0", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9cca35f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128009 + ], + "max_length": 4096, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.33.0" +} diff --git a/pytorch_model-00001-of-00004.bin b/pytorch_model-00001-of-00004.bin new file mode 100644 index 0000000..04dbb32 --- /dev/null +++ b/pytorch_model-00001-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c65ab6dba34e166f5eca952765f1d7781de7632b402d296be46dac906eb20575 +size 4976717314 diff --git a/pytorch_model-00002-of-00004.bin b/pytorch_model-00002-of-00004.bin new file mode 100644 index 0000000..2796989 --- /dev/null +++ b/pytorch_model-00002-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded33617aef6da17dd2c75c8ea7833ff9f1b245b263699ef1faa9569c2467e7d +size 4999826246 diff --git a/pytorch_model-00003-of-00004.bin b/pytorch_model-00003-of-00004.bin new file mode 100644 index 0000000..670c9c4 --- /dev/null +++ b/pytorch_model-00003-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b1d51fb6e7658552016c011cb0fb66d3b9b43a9c3490d9ca17be0d243892f30 +size 4915938762 diff --git a/pytorch_model-00004-of-00004.bin b/pytorch_model-00004-of-00004.bin new file mode 100644 index 0000000..6e81a32 --- /dev/null +++ b/pytorch_model-00004-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:170fd0b939fde6f3e3fd63dbb4b4962d72d70c9fa2ed535e0ebb38afc983e343 +size 1168140873 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..7be15ca --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00004-of-00004.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.norm.weight": "pytorch_model-00004-of-00004.bin" + } +}