初始化项目，由ModelHub XC社区提供模型

Model: MiniLLM/SFT-OPT-6.7B
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,34 @@
+---
+license: apache-2.0
+datasets:
+- databricks/databricks-dolly-15k
+language:
+- en
+metrics:
+- rouge
+base_model:
+- facebook/opt-6.7B
+pipeline_tag: text-generation
+---
+# SFT-OPT-6.7B
+
+[paper](https://arxiv.org/abs/2306.08543) | [code](https://github.com/microsoft/LMOps/tree/main/minillm)
+
+**SFT-OPT-6.7B** is an OPT-6.7B model supervised fine-tuned on [databricks-dolly-15k](https://huggingface.co/datasets/aisquared/databricks-dolly-15k).
+
+It is used as a baseline for [MiniLLM](https://huggingface.co/MiniLLM/MiniLLM-OPT-6.7B).
+
+## Other Baselines
++ [KD](https://huggingface.co/MiniLLM/KD-OPT-6.7B)
++ [SeqKD](https://huggingface.co/MiniLLM/SeqKD-OPT-6.7B)
+
+
+## Citation
+```
+@inproceedings{minillm,
+  title={MiniLLM: Knowledge Distillation of Large Language Models},
+  author={Gu, Yuxian and Dong, Li and Wei, Furu and Huang, Minlie},
+  booktitle={Proceedings of ICLR},
+  year={2024}
+}
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/data/yuxian/MiniLLM_dir/results/opt/train/sft/opt-6.7B",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 16384,
+  "hidden_size": 4096,
+  "init_std": 0.02,
+  "is_model_parallel": true,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float16",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 4096
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.0.dev0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ac6ad7d78917d426a66f59e49ebb19e4f99a4d89be24689c557276e9d971f8
+size 4993326868

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9167d7f0ae104fd872629de6ebb9e91fcdb76ed9664be6b70439c645943bbb
+size 4967433288

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314253513b2ec925aac057274457b778ce53a500329e465dc675725bab7d22c3
+size 3356364946

pytorch_model.bin.index.json

@@ -0,0 +1,524 @@
+{
+  "metadata": {
+    "total_size": 13316947968
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.embed_positions.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.11.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.12.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.20.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.23.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.24.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.3.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.30.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.fc1.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.fc1.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.fc2.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.fc2.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.layers.4.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}