Update checkpoint to fix huggingface error

README.md

@@ -1,49 +1,55 @@
 ---
-license: mit
+language:
+- eng_Latn
+- zho_Hans
+license: cc-by-nc-4.0
+tags:
+- generated_from_trainer
+model-index:
+- name: 3.3B_nllb_bracket_idx
+  results: []
 ---
 
-- Paper link: [Frustratingly Easy Label Projection for Cross-lingual Transfer](https://arxiv.org/abs/2211.15613)
-- Github link: https://github.com/edchengg/easyproject
-- Please use the transformers==4.29.2 library as Huggingface recently fixed a bug in [NLLB tokenizer](https://github.com/huggingface/transformers/pull/22313)
-
-# Code
-```python
-from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
-import torch
-
-tokenizer = AutoTokenizer.from_pretrained(
-        "facebook/nllb-200-distilled-600M",  src_lang="eng_Latn")
-    
-print("Loading model")
-model = AutoModelForSeq2SeqLM.from_pretrained("ychenNLP/nllb-200-3.3b-easyproject")
-model.cuda()
-
-input_chunks = ["A translator always risks inadvertently introducing source-language words, grammar, or syntax into the target-language rendering."]
-print("Start translation...")
-output_result = []
-
-batch_size = 1
-for idx in tqdm(range(0, len(input_chunks), batch_size)):
-    start_idx = idx
-    end_idx = idx + batch_size
-    inputs = tokenizer(input_chunks[start_idx: end_idx], padding=True, truncation=True, max_length=128, return_tensors="pt").to('cuda')
-
-    with torch.no_grad():
-        translated_tokens = model.generate(**inputs, forced_bos_token_id=tokenizer.lang_code_to_id["zho_Hans"], 
-                        max_length=128, num_beams=5, num_return_sequences=1, early_stopping=True)
-
-    output = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)
-    output_result.extend(output)
-print(output_result)
-```
-
-## Citation
-
-```
-@inproceedings{chen2023easyproject,
-  title={Frustratingly Easy Label Projection for Cross-lingual Transfer},
-  author={Chen, Yang and Jiang, Chao and Ritter, Alan and Xu, Wei},
-  booktitle={Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Findings)},
-  year={2023}
-}
-```
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# 3.3B_nllb_bracket_idx
+
+This model is a fine-tuned version of [facebook/nllb-200-3.3B](https://huggingface.co/facebook/nllb-200-3.3B) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- training_steps: 1000
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.29.2
+- Pytorch 1.11.0+cu113
+- Datasets 2.8.0
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "facebook/nllb-200-3.3B",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "M2M100ForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "d_model": 2048,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 8192,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 8192,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 24,
+  "eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "m2m_100",
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 256206
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 200,
+  "pad_token_id": 1,
+  "transformers_version": "4.29.2"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af59754ba97be1c0e2b4346ad7af9229cc042f082bdfe41f2ca5dc6bebb009f2
+size 6941786709

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2714171d9351dab45df28fbc3e3b22a1f7ddaaa615621f079a9af104146c2141
+size 8553663337

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1136f429ec6765793f956c63b25e2d858e6b06e29f95f9d92894392fd65481
+size 2098840299

pytorch_model.bin.index.json

@@ -0,0 +1,1025 @@
+{
+  "metadata": {
+    "total_size": 19692781568
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.decoder.embed_positions.weights": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.embed_tokens.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.encoder_attn_layer_norm.weight": "pytorch_model-00002-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-00002-of-00003.bin",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.12.encoder_attn_layer_norm.weight": "pytorch_model-00002-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.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.13.encoder_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.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.14.encoder_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.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.15.encoder_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.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.16.encoder_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.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.17.encoder_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.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.18.encoder_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.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.19.encoder_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.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.20.encoder_attn_layer_norm.weight": "pytorch_model-00002-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.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.21.encoder_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.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.22.encoder_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.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.encoder_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-00002-of-00003.bin",
+    "model.decoder.layers.23.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00002-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.3.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.encoder_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.encoder_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.encoder_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.encoder_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.fc1.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.fc1.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.fc2.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.fc2.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.encoder.embed_positions.weights": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.fc1.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.fc1.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.fc2.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.fc2.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
+    "model.encoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.shared.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcde1668a62ddf12ecc5f51dbb7517de8d0a7cb4d7855e902e637c0d2104e704
+size 14503

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
+size 4852054

special_tokens_map.json

@@ -0,0 +1,219 @@
+{
+  "additional_special_tokens": [
+    "ace_Arab",
+    "ace_Latn",
+    "acm_Arab",
+    "acq_Arab",
+    "aeb_Arab",
+    "afr_Latn",
+    "ajp_Arab",
+    "aka_Latn",
+    "amh_Ethi",
+    "apc_Arab",
+    "arb_Arab",
+    "ars_Arab",
+    "ary_Arab",
+    "arz_Arab",
+    "asm_Beng",
+    "ast_Latn",
+    "awa_Deva",
+    "ayr_Latn",
+    "azb_Arab",
+    "azj_Latn",
+    "bak_Cyrl",
+    "bam_Latn",
+    "ban_Latn",
+    "bel_Cyrl",
+    "bem_Latn",
+    "ben_Beng",
+    "bho_Deva",
+    "bjn_Arab",
+    "bjn_Latn",
+    "bod_Tibt",
+    "bos_Latn",
+    "bug_Latn",
+    "bul_Cyrl",
+    "cat_Latn",
+    "ceb_Latn",
+    "ces_Latn",
+    "cjk_Latn",
+    "ckb_Arab",
+    "crh_Latn",
+    "cym_Latn",
+    "dan_Latn",
+    "deu_Latn",
+    "dik_Latn",
+    "dyu_Latn",
+    "dzo_Tibt",
+    "ell_Grek",
+    "eng_Latn",
+    "epo_Latn",
+    "est_Latn",
+    "eus_Latn",
+    "ewe_Latn",
+    "fao_Latn",
+    "pes_Arab",
+    "fij_Latn",
+    "fin_Latn",
+    "fon_Latn",
+    "fra_Latn",
+    "fur_Latn",
+    "fuv_Latn",
+    "gla_Latn",
+    "gle_Latn",
+    "glg_Latn",
+    "grn_Latn",
+    "guj_Gujr",
+    "hat_Latn",
+    "hau_Latn",
+    "heb_Hebr",
+    "hin_Deva",
+    "hne_Deva",
+    "hrv_Latn",
+    "hun_Latn",
+    "hye_Armn",
+    "ibo_Latn",
+    "ilo_Latn",
+    "ind_Latn",
+    "isl_Latn",
+    "ita_Latn",
+    "jav_Latn",
+    "jpn_Jpan",
+    "kab_Latn",
+    "kac_Latn",
+    "kam_Latn",
+    "kan_Knda",
+    "kas_Arab",
+    "kas_Deva",
+    "kat_Geor",
+    "knc_Arab",
+    "knc_Latn",
+    "kaz_Cyrl",
+    "kbp_Latn",
+    "kea_Latn",
+    "khm_Khmr",
+    "kik_Latn",
+    "kin_Latn",
+    "kir_Cyrl",
+    "kmb_Latn",
+    "kon_Latn",
+    "kor_Hang",
+    "kmr_Latn",
+    "lao_Laoo",
+    "lvs_Latn",
+    "lij_Latn",
+    "lim_Latn",
+    "lin_Latn",
+    "lit_Latn",
+    "lmo_Latn",
+    "ltg_Latn",
+    "ltz_Latn",
+    "lua_Latn",
+    "lug_Latn",
+    "luo_Latn",
+    "lus_Latn",
+    "mag_Deva",
+    "mai_Deva",
+    "mal_Mlym",
+    "mar_Deva",
+    "min_Latn",
+    "mkd_Cyrl",
+    "plt_Latn",
+    "mlt_Latn",
+    "mni_Beng",
+    "khk_Cyrl",
+    "mos_Latn",
+    "mri_Latn",
+    "zsm_Latn",
+    "mya_Mymr",
+    "nld_Latn",
+    "nno_Latn",
+    "nob_Latn",
+    "npi_Deva",
+    "nso_Latn",
+    "nus_Latn",
+    "nya_Latn",
+    "oci_Latn",
+    "gaz_Latn",
+    "ory_Orya",
+    "pag_Latn",
+    "pan_Guru",
+    "pap_Latn",
+    "pol_Latn",
+    "por_Latn",
+    "prs_Arab",
+    "pbt_Arab",
+    "quy_Latn",
+    "ron_Latn",
+    "run_Latn",
+    "rus_Cyrl",
+    "sag_Latn",
+    "san_Deva",
+    "sat_Beng",
+    "scn_Latn",
+    "shn_Mymr",
+    "sin_Sinh",
+    "slk_Latn",
+    "slv_Latn",
+    "smo_Latn",
+    "sna_Latn",
+    "snd_Arab",
+    "som_Latn",
+    "sot_Latn",
+    "spa_Latn",
+    "als_Latn",
+    "srd_Latn",
+    "srp_Cyrl",
+    "ssw_Latn",
+    "sun_Latn",
+    "swe_Latn",
+    "swh_Latn",
+    "szl_Latn",
+    "tam_Taml",
+    "tat_Cyrl",
+    "tel_Telu",
+    "tgk_Cyrl",
+    "tgl_Latn",
+    "tha_Thai",
+    "tir_Ethi",
+    "taq_Latn",
+    "taq_Tfng",
+    "tpi_Latn",
+    "tsn_Latn",
+    "tso_Latn",
+    "tuk_Latn",
+    "tum_Latn",
+    "tur_Latn",
+    "twi_Latn",
+    "tzm_Tfng",
+    "uig_Arab",
+    "ukr_Cyrl",
+    "umb_Latn",
+    "urd_Arab",
+    "uzn_Latn",
+    "vec_Latn",
+    "vie_Latn",
+    "war_Latn",
+    "wol_Latn",
+    "xho_Latn",
+    "ydd_Hebr",
+    "yor_Latn",
+    "yue_Hant",
+    "zho_Hans",
+    "zho_Hant",
+    "zul_Latn"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": null,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "legacy_behaviour": false,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "NllbTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>"
+}