Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+---
+
+# Model Trained Using AutoTrain

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/content/drive/MyDrive/Llama-2-13B-Nous-Hermes-vicuna-uncensored-mastermod",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f7bae8d7789753d9a114b1d14c6028d4207d081a92b12b0af5454aea788e70
+size 52487757

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

checkpoint-204/README.md

@@ -0,0 +1,32 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+- PEFT 0.5.0.dev0
+
+- PEFT 0.5.0.dev0

checkpoint-204/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/content/drive/MyDrive/Llama-2-13B-Nous-Hermes-vicuna-uncensored-mastermod",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-204/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f7bae8d7789753d9a114b1d14c6028d4207d081a92b12b0af5454aea788e70
+size 52487757

checkpoint-204/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

checkpoint-204/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550593460a2bba50da991a59e6789757f24c9fbefb286aaa1b7af99bc6bb786a
+size 104992261

checkpoint-204/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
+size 443

checkpoint-204/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e414f3a3870afed00637c6b76749d97f44dea4436b6cc7d21b058f84864a1cad
+size 14575

checkpoint-204/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4c392f08847d6994d1da76873290949c7b99dc676c522e4c79ba03d0650bf7
+size 627

checkpoint-204/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-204/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-204/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-204/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0002688524590163934,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00020327868852459014,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00013770491803278688,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 7.21311475409836e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 6.5573770491803276e-06,
+      "loss": 0.0,
+      "step": 200
+    }
+  ],
+  "max_steps": 204,
+  "num_train_epochs": 1,
+  "total_flos": 1.456536337514496e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-204/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f4df1e960443017598931077cf961429b7dae0c6032641e275b096f849a11e
+size 4091

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/Llama-2-13B-Nous-Hermes-vicuna-uncensored-mastermod",
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "init_std": 0.02,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 4096,
+  "model_type": "opt",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32032,
+  "word_embed_proj_dim": 5120
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.32.0.dev0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec32dd5c545e8d3f65278a368c03d28a4b2a36d3ed795539e7bb9c07c6063632
+size 9968109713

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d924bbe3bc3291f3bbaa9622216ee9a67300988428c8971729d2c7907fcd0575
+size 1639235613

pytorch_model.bin.index.json

@@ -0,0 +1,652 @@
+{
+  "metadata": {
+    "total_size": 11607121920
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.embed_positions.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.32.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.33.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.34.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.35.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.35.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.35.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.35.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.36.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.37.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.38.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.39.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.4.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

runs/Jul31_23-17-56_07c9d996ff38/events.out.tfevents.1690845476.07c9d996ff38.25152.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7ca82e9fa3f7025b388cd6f854801e6ef6d97868b6d778a27377029a2d79be
+size 6021

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f4df1e960443017598931077cf961429b7dae0c6032641e275b096f849a11e
+size 4091