SFT_phi2_hh-rlhf_epoch1-subset131adapter

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: microsoft/phi-2
+model-index:
+- name: SFT_phi2_hh-rlhf_epoch1-subset131
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# SFT_phi2_hh-rlhf_epoch1-subset131
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "fc2",
+    "fc1",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.38.2"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f23de020c56791e189fe3e06540f793cd97e26f7bea97e21d4ed008b887e4b8
+size 9991225919

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c0c3e9dffc4df1fa873ca7a778a209685678ba4cfeb23a2575aec112e831ae
+size 1127670150

pytorch_model.bin.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 11118735360
+  },
+  "weight_map": {
+    "lm_head.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.final_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.final_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

runs/Apr08_17-44-18_GPUServer1-GPU5/events.out.tfevents.1712594658.GPUServer1-GPU5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f58e05e025b6365689c3be65f3041292573c0947854a838b0ffca467391097d
+size 7906

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,324 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8705fa85732d18fbfb0e76f15a11fe59ef9541d36bcafc84799d7e3c5f657f1d
+size 4984