Duplicate from facebook/musicgen-large

Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,233 @@
+---
+inference: true
+tags:
+- musicgen
+license: cc-by-nc-4.0
+---
+
+# MusicGen - Large - 3.3B
+
+MusicGen is a text-to-music model capable of genreating high-quality music samples conditioned on text descriptions or audio prompts.
+It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz. 
+Unlike existing methods, like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebooks in one pass. 
+By introducing a small delay between the codebooks, we show we can predict them in parallel, thus having only 50 auto-regressive steps per second of audio.
+
+MusicGen was published in [Simple and Controllable Music Generation](https://arxiv.org/abs/2306.05284) by *Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, Alexandre Défossez*.
+
+Four checkpoints are released:
+- [small](https://huggingface.co/facebook/musicgen-small)
+- [medium](https://huggingface.co/facebook/musicgen-medium)
+- [**large** (this checkpoint)](https://huggingface.co/facebook/musicgen-large)
+- [melody](https://huggingface.co/facebook/musicgen-melody)
+
+## Example
+
+Try out MusicGen yourself!
+
+* Audiocraft Colab:
+
+<a target="_blank" href="https://colab.research.google.com/drive/1fxGqfg96RBUvGxZ1XXN07s3DthrKUl4-?usp=sharing">
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
+</a>
+
+* Hugging Face Colab:
+
+<a target="_blank" href="https://colab.research.google.com/github/sanchit-gandhi/notebooks/blob/main/MusicGen.ipynb"> 
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> 
+</a>
+
+* Hugging Face Demo:
+
+<a target="_blank" href="https://huggingface.co/spaces/facebook/MusicGen">
+  <img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg" alt="Open in HuggingFace"/>
+</a>
+
+## 🤗 Transformers Usage
+
+You can run MusicGen locally with the 🤗 Transformers library from version 4.31.0 onwards.
+
+1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers) and scipy:
+
+```
+pip install --upgrade pip
+pip install --upgrade transformers scipy
+```
+
+2. Run inference via the `Text-to-Audio` (TTA) pipeline. You can infer the MusicGen model via the TTA pipeline in just a few lines of code!
+
+```python
+from transformers import pipeline
+import scipy
+
+synthesiser = pipeline("text-to-audio", "facebook/musicgen-large")
+
+music = synthesiser("lo-fi music with a soothing melody", forward_params={"do_sample": True})
+
+scipy.io.wavfile.write("musicgen_out.wav", rate=music["sampling_rate"], data=music["audio"])
+```
+
+3. Run inference via the Transformers modelling code. You can use the processor + generate code to convert text into a mono 32 kHz audio waveform for more fine-grained control.
+
+```python
+from transformers import AutoProcessor, MusicgenForConditionalGeneration
+
+processor = AutoProcessor.from_pretrained("facebook/musicgen-large")
+model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-large")
+
+inputs = processor(
+    text=["80s pop track with bassy drums and synth", "90s rock song with loud guitars and heavy drums"],
+    padding=True,
+    return_tensors="pt",
+)
+
+audio_values = model.generate(**inputs, max_new_tokens=256)
+```
+
+4. Listen to the audio samples either in an ipynb notebook:
+
+```python
+from IPython.display import Audio
+
+sampling_rate = model.config.audio_encoder.sampling_rate
+Audio(audio_values[0].numpy(), rate=sampling_rate)
+```
+
+Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
+
+```python
+import scipy
+
+sampling_rate = model.config.audio_encoder.sampling_rate
+scipy.io.wavfile.write("musicgen_out.wav", rate=sampling_rate, data=audio_values[0, 0].numpy())
+```
+
+For more details on using the MusicGen model for inference using the 🤗 Transformers library, refer to the [MusicGen docs](https://huggingface.co/docs/transformers/model_doc/musicgen).
+
+## Audiocraft Usage
+
+You can also run MusicGen locally through the original [Audiocraft library]((https://github.com/facebookresearch/audiocraft):
+
+1. First install the [`audiocraft` library](https://github.com/facebookresearch/audiocraft)
+```
+pip install git+https://github.com/facebookresearch/audiocraft.git
+```
+
+2. Make sure to have [`ffmpeg`](https://ffmpeg.org/download.html) installed:
+```
+apt get install ffmpeg
+```
+
+3. Run the following Python code:
+
+```py
+from audiocraft.models import MusicGen
+from audiocraft.data.audio import audio_write
+
+model = MusicGen.get_pretrained("large")
+model.set_generation_params(duration=8)  # generate 8 seconds.
+
+descriptions = ["happy rock", "energetic EDM"]
+
+wav = model.generate(descriptions)  # generates 2 samples.
+
+for idx, one_wav in enumerate(wav):
+    # Will save under {idx}.wav, with loudness normalization at -14 db LUFS.
+    audio_write(f'{idx}', one_wav.cpu(), model.sample_rate, strategy="loudness")
+```
+
+## Model details
+
+**Organization developing the model:** The FAIR team of Meta AI.
+
+**Model date:** MusicGen was trained between April 2023 and May 2023.
+
+**Model version:** This is the version 1 of the model.
+
+**Model type:** MusicGen consists of an EnCodec model for audio tokenization, an auto-regressive language model based on the transformer architecture for music modeling. The model comes in different sizes: 300M, 1.5B and 3.3B parameters ; and two variants: a model trained for text-to-music generation task and a model trained for melody-guided music generation.
+
+**Paper or resources for more information:** More information can be found in the paper [Simple and Controllable Music Generation](https://arxiv.org/abs/2306.05284).
+
+**Citation details:**
+```
+@misc{copet2023simple,
+      title={Simple and Controllable Music Generation}, 
+      author={Jade Copet and Felix Kreuk and Itai Gat and Tal Remez and David Kant and Gabriel Synnaeve and Yossi Adi and Alexandre Défossez},
+      year={2023},
+      eprint={2306.05284},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD}
+}
+```
+
+**License:** Code is released under MIT, model weights are released under CC-BY-NC 4.0.
+
+**Where to send questions or comments about the model:** Questions and comments about MusicGen can be sent via the [Github repository](https://github.com/facebookresearch/audiocraft) of the project, or by opening an issue.
+
+## Intended use
+**Primary intended use:** The primary use of MusicGen is research on AI-based music generation, including:
+
+- Research efforts, such as probing and better understanding the limitations of generative models to further improve the state of science
+- Generation of music guided by text or melody to understand current abilities of generative AI models by machine learning amateurs
+
+**Primary intended users:** The primary intended users of the model are researchers in audio, machine learning and artificial intelligence, as well as amateur seeking to better understand those models.
+
+**Out-of-scope use cases:** The model should not be used on downstream applications without further risk evaluation and mitigation. The model should not be used to intentionally create or disseminate music pieces that create hostile or alienating environments for people. This includes generating music that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
+
+## Metrics
+
+**Models performance measures:** We used the following objective measure to evaluate the model on a standard music benchmark:
+
+- Frechet Audio Distance computed on features extracted from a pre-trained audio classifier (VGGish)
+- Kullback-Leibler Divergence on label distributions extracted from a pre-trained audio classifier (PaSST)
+- CLAP Score between audio embedding and text embedding extracted from a pre-trained CLAP model
+
+Additionally, we run qualitative studies with human participants, evaluating the performance of the model with the following axes:
+
+- Overall quality of the music samples;
+- Text relevance to the provided text input;
+- Adherence to the melody for melody-guided music generation.
+
+More details on performance measures and human studies can be found in the paper.
+
+**Decision thresholds:** Not applicable.
+
+## Evaluation datasets
+
+The model was evaluated on the [MusicCaps benchmark](https://www.kaggle.com/datasets/googleai/musiccaps) and on an in-domain held-out evaluation set, with no artist overlap with the training set.
+
+## Training datasets
+
+The model was trained on licensed data using the following sources: the [Meta Music Initiative Sound Collection](https://www.fb.com/sound), [Shutterstock music collection](https://www.shutterstock.com/music) and the [Pond5 music collection](https://www.pond5.com/). See the paper for more details about the training set and corresponding preprocessing.
+
+## Evaluation results
+
+Below are the objective metrics obtained on MusicCaps with the released model. Note that for the publicly released models, we had all the datasets go through a state-of-the-art music source separation method, namely using the open source [Hybrid Transformer for Music Source Separation](https://github.com/facebookresearch/demucs) (HT-Demucs), in order to keep only the instrumental part. This explains the difference in objective metrics with the models used in the paper.
+
+| Model | Frechet Audio Distance | KLD | Text Consistency | Chroma Cosine Similarity |
+|---|---|---|---|---|
+| facebook/musicgen-small  | 4.88 | 1.42 | 0.27 | - |
+| facebook/musicgen-medium | 5.14 | 1.38 | 0.28 | - |
+| **facebook/musicgen-large**  | 5.48 | 1.37 | 0.28 | - |
+| facebook/musicgen-melody | 4.93 | 1.41 | 0.27 | 0.44 |
+
+More information can be found in the paper [Simple and Controllable Music Generation](https://arxiv.org/abs/2306.05284), in the Results section.
+
+## Limitations and biases
+
+**Data:** The data sources used to train the model are created by music professionals and covered by legal agreements with the right holders. The model is trained on 20K hours of data, we believe that scaling the model on larger datasets can further improve the performance of the model.
+
+**Mitigations:** Vocals have been removed from the data source using corresponding tags, and then using a state-of-the-art music source separation method, namely using the open source [Hybrid Transformer for Music Source Separation](https://github.com/facebookresearch/demucs) (HT-Demucs).
+
+**Limitations:**
+
+- The model is not able to generate realistic vocals.
+- The model has been trained with English descriptions and will not perform as well in other languages.
+- The model does not perform equally well for all music styles and cultures.
+- The model sometimes generates end of songs, collapsing to silence.
+- It is sometimes difficult to assess what types of text descriptions provide the best generations. Prompt engineering may be required to obtain satisfying results.
+
+**Biases:** The source of data is potentially lacking diversity and all music cultures are not equally represented in the dataset. The model may not perform equally well on the wide variety of music genres that exists. The generated samples from the model will reflect the biases from the training data. Further work on this model should include methods for balanced and just representations of cultures, for example, by scaling the training data to be both diverse and inclusive.
+
+**Risks and harms:** Biases and limitations of the model may lead to generation of samples that may be considered as biased, inappropriate or offensive. We believe that providing the code to reproduce the research and train new models will allow to broaden the application to new and more representative data.
+
+**Use cases:** Users must be aware of the biases, limitations and risks of the model. MusicGen is a model developed for artificial intelligence research on controllable music generation. As such, it should not be used for downstream applications without further investigation and mitigation of risks.

compression_state_dict.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37d256b525d4117f8bbf790ab448a8e9f4746cd401900fe1ae72e154b1513a30
+size 236001935

config.json

@@ -0,0 +1,298 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "MusicgenForConditionalGeneration"
+  ],
+  "audio_encoder": {
+    "_name_or_path": "facebook/encodec_32khz",
+    "add_cross_attention": false,
+    "architectures": [
+      "EncodecModel"
+    ],
+    "audio_channels": 1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_length_s": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_dim": 128,
+    "codebook_size": 2048,
+    "compress": 2,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dilation_growth_rate": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 128,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "kernel_size": 7,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "last_kernel_size": 7,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "encodec",
+    "no_repeat_ngram_size": 0,
+    "norm_type": "weight_norm",
+    "normalize": false,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_filters": 64,
+    "num_lstm_layers": 2,
+    "num_residual_layers": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "overlap": null,
+    "pad_mode": "reflect",
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "residual_kernel_size": 3,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 32000,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "target_bandwidths": [
+      2.2
+    ],
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.31.0.dev0",
+    "trim_right_ratio": 1.0,
+    "typical_p": 1.0,
+    "upsampling_ratios": [
+      8,
+      5,
+      4,
+      4
+    ],
+    "use_bfloat16": false,
+    "use_causal_conv": false,
+    "use_conv_shortcut": false
+  },
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 2048,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 8192,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 2048,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 2048,
+    "min_length": 0,
+    "model_type": "musicgen_decoder",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 4,
+    "num_hidden_layers": 48,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 2048,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.31.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 2048
+  },
+  "is_encoder_decoder": true,
+  "model_type": "musicgen",
+  "text_encoder": {
+    "_name_or_path": "t5-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 3072,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "relu",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "feed_forward_proj": "relu",
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "is_gated_act": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "t5",
+    "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "summarization": {
+        "early_stopping": true,
+        "length_penalty": 2.0,
+        "max_length": 200,
+        "min_length": 30,
+        "no_repeat_ngram_size": 3,
+        "num_beams": 4,
+        "prefix": "summarize: "
+      },
+      "translation_en_to_de": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to German: "
+      },
+      "translation_en_to_fr": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to French: "
+      },
+      "translation_en_to_ro": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to Romanian: "
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.31.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2048,
+  "decoder_start_token_id": 2048,
+  "do_sample": true,
+  "guidance_scale": 3.0,
+  "max_length": 1500,
+  "pad_token_id": 2048,
+  "transformers_version": "4.31.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "chunk_length_s": null,
+  "feature_extractor_type": "EncodecFeatureExtractor",
+  "feature_size": 1,
+  "overlap": null,
+  "padding_side": "left",
+  "padding_value": 0.0,
+  "processor_class": "MusicgenProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 32000
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ed8a0d95eff206263d1ae62955a7b8a7dab11a6b55e953887aea6ed54f85bd
+size 9987827539

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9923d2947297a9883404abfd4041a32cf486c763d36e00eb4f178823bf6bdac
+size 3731608779

pytorch_model.bin.index.json

@@ -0,0 +1,1004 @@
+{
+  "metadata": {
+    "total_size": 13719079192
+  },
+  "weight_map": {
+    "audio_encoder.decoder.layers.0.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.0.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.0.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.1.lstm.bias_hh_l0": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.1.lstm.bias_hh_l1": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.1.lstm.bias_ih_l0": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.1.lstm.bias_ih_l1": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.1.lstm.weight_hh_l0": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.1.lstm.weight_hh_l1": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.1.lstm.weight_ih_l0": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.1.lstm.weight_ih_l1": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.10.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.10.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.10.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.10.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.10.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.10.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.12.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.12.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.12.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.13.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.13.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.13.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.13.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.13.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.13.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.15.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.15.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.15.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.3.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.4.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.4.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.4.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.4.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.4.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.4.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.6.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.6.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.6.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.7.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.7.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.7.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.7.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.7.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.7.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.9.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.9.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.decoder.layers.9.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.0.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.0.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.0.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.1.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.1.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.1.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.1.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.1.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.1.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.10.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.10.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.10.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.10.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.10.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.10.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.12.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.12.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.12.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.13.lstm.bias_hh_l0": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.13.lstm.bias_hh_l1": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.13.lstm.bias_ih_l0": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.13.lstm.bias_ih_l1": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.13.lstm.weight_hh_l0": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.13.lstm.weight_hh_l1": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.13.lstm.weight_ih_l0": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.13.lstm.weight_ih_l1": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.15.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.15.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.15.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.3.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.4.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.4.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.4.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.4.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.4.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.4.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.6.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.6.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.6.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.7.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.7.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.7.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.7.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.7.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.7.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.9.conv.bias": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.9.conv.weight_g": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.encoder.layers.9.conv.weight_v": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.0.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.0.codebook.embed": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.0.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.0.codebook.inited": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.1.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.1.codebook.embed": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.1.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.1.codebook.inited": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.2.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.2.codebook.embed": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.2.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.2.codebook.inited": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.3.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.3.codebook.embed": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.3.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
+    "audio_encoder.quantizer.layers.3.codebook.inited": "pytorch_model-00001-of-00002.bin",
+    "decoder.lm_heads.0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.lm_heads.1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.lm_heads.2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.lm_heads.3.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.embed_positions.weights": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.embed_tokens.0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.embed_tokens.1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.embed_tokens.2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.embed_tokens.3.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.0.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.32.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.33.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.34.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.34.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.34.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.34.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.34.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.34.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.34.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.34.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.34.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.34.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.34.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.34.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.34.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.34.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.34.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.34.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.35.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.35.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.36.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.37.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.38.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.39.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.4.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.40.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.40.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.41.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.42.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.43.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.44.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.45.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.46.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.47.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.model.decoder.layers.5.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "decoder.model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "enc_to_dec_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "enc_to_dec_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "text_encoder.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "text_encoder.shared.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

state_dict.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f0cf17b5e65c5dd8ba71767371c377f174e4ce1db44bc4d6657825769f26ffd
+size 6514108999

tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "processor_class": "MusicgenProcessor",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}