Commit
•
160ccb2
0
Parent(s):
Duplicate from facebook/musicgen-large
Browse filesCo-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>
- .gitattributes +34 -0
- README.md +221 -0
- compression_state_dict.bin +3 -0
- config.json +298 -0
- generation_config.json +10 -0
- preprocessor_config.json +11 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +1004 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- state_dict.bin +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +112 -0
.gitattributes
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,221 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
inference: false
|
| 3 |
+
tags:
|
| 4 |
+
- musicgen
|
| 5 |
+
license: cc-by-nc-4.0
|
| 6 |
+
duplicated_from: facebook/musicgen-large
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# MusicGen - Large - 3.3B
|
| 10 |
+
|
| 11 |
+
MusicGen is a text-to-music model capable of genreating high-quality music samples conditioned on text descriptions or audio prompts.
|
| 12 |
+
It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz.
|
| 13 |
+
Unlike existing methods, like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebooks in one pass.
|
| 14 |
+
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.
|
| 15 |
+
|
| 16 |
+
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*.
|
| 17 |
+
|
| 18 |
+
Four checkpoints are released:
|
| 19 |
+
- [small](https://huggingface.co/facebook/musicgen-small)
|
| 20 |
+
- [medium](https://huggingface.co/facebook/musicgen-medium)
|
| 21 |
+
- [**large** (this checkpoint)](https://huggingface.co/facebook/musicgen-large)
|
| 22 |
+
- [melody](https://huggingface.co/facebook/musicgen-melody)
|
| 23 |
+
|
| 24 |
+
## Example
|
| 25 |
+
|
| 26 |
+
Try out MusicGen yourself!
|
| 27 |
+
|
| 28 |
+
* Audiocraft Colab:
|
| 29 |
+
|
| 30 |
+
<a target="_blank" href="https://colab.research.google.com/drive/1fxGqfg96RBUvGxZ1XXN07s3DthrKUl4-?usp=sharing">
|
| 31 |
+
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
|
| 32 |
+
</a>
|
| 33 |
+
|
| 34 |
+
* Hugging Face Colab:
|
| 35 |
+
|
| 36 |
+
<a target="_blank" href="https://colab.research.google.com/github/sanchit-gandhi/notebooks/blob/main/MusicGen.ipynb">
|
| 37 |
+
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
|
| 38 |
+
</a>
|
| 39 |
+
|
| 40 |
+
* Hugging Face Demo:
|
| 41 |
+
|
| 42 |
+
<a target="_blank" href="https://huggingface.co/spaces/facebook/MusicGen">
|
| 43 |
+
<img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg" alt="Open in HuggingFace"/>
|
| 44 |
+
</a>
|
| 45 |
+
|
| 46 |
+
## 🤗 Transformers Usage
|
| 47 |
+
|
| 48 |
+
You can run MusicGen locally with the 🤗 Transformers library from version 4.31.0 onwards.
|
| 49 |
+
|
| 50 |
+
1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers) from main:
|
| 51 |
+
|
| 52 |
+
```
|
| 53 |
+
pip install git+https://github.com/huggingface/transformers.git
|
| 54 |
+
```
|
| 55 |
+
|
| 56 |
+
2. Run the following Python code to generate text-conditional audio samples:
|
| 57 |
+
|
| 58 |
+
```py
|
| 59 |
+
from transformers import AutoProcessor, MusicgenForConditionalGeneration
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
processor = AutoProcessor.from_pretrained("facebook/musicgen-large")
|
| 63 |
+
model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-large")
|
| 64 |
+
|
| 65 |
+
inputs = processor(
|
| 66 |
+
text=["80s pop track with bassy drums and synth", "90s rock song with loud guitars and heavy drums"],
|
| 67 |
+
padding=True,
|
| 68 |
+
return_tensors="pt",
|
| 69 |
+
)
|
| 70 |
+
|
| 71 |
+
audio_values = model.generate(**inputs, max_new_tokens=256)
|
| 72 |
+
```
|
| 73 |
+
|
| 74 |
+
3. Listen to the audio samples either in an ipynb notebook:
|
| 75 |
+
|
| 76 |
+
```py
|
| 77 |
+
from IPython.display import Audio
|
| 78 |
+
|
| 79 |
+
sampling_rate = model.config.audio_encoder.sampling_rate
|
| 80 |
+
Audio(audio_values[0].numpy(), rate=sampling_rate)
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
+
Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
|
| 84 |
+
|
| 85 |
+
```py
|
| 86 |
+
import scipy
|
| 87 |
+
|
| 88 |
+
sampling_rate = model.config.audio_encoder.sampling_rate
|
| 89 |
+
scipy.io.wavfile.write("musicgen_out.wav", rate=sampling_rate, data=audio_values[0, 0].numpy())
|
| 90 |
+
```
|
| 91 |
+
|
| 92 |
+
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).
|
| 93 |
+
|
| 94 |
+
## Audiocraft Usage
|
| 95 |
+
|
| 96 |
+
You can also run MusicGen locally through the original [Audiocraft library]((https://github.com/facebookresearch/audiocraft):
|
| 97 |
+
|
| 98 |
+
1. First install the [`audiocraft` library](https://github.com/facebookresearch/audiocraft)
|
| 99 |
+
```
|
| 100 |
+
pip install git+https://github.com/facebookresearch/audiocraft.git
|
| 101 |
+
```
|
| 102 |
+
|
| 103 |
+
2. Make sure to have [`ffmpeg`](https://ffmpeg.org/download.html) installed:
|
| 104 |
+
```
|
| 105 |
+
apt get install ffmpeg
|
| 106 |
+
```
|
| 107 |
+
|
| 108 |
+
3. Run the following Python code:
|
| 109 |
+
|
| 110 |
+
```py
|
| 111 |
+
from audiocraft.models import MusicGen
|
| 112 |
+
from audiocraft.data.audio import audio_write
|
| 113 |
+
|
| 114 |
+
model = MusicGen.get_pretrained("large")
|
| 115 |
+
model.set_generation_params(duration=8) # generate 8 seconds.
|
| 116 |
+
|
| 117 |
+
descriptions = ["happy rock", "energetic EDM"]
|
| 118 |
+
|
| 119 |
+
wav = model.generate(descriptions) # generates 2 samples.
|
| 120 |
+
|
| 121 |
+
for idx, one_wav in enumerate(wav):
|
| 122 |
+
# Will save under {idx}.wav, with loudness normalization at -14 db LUFS.
|
| 123 |
+
audio_write(f'{idx}', one_wav.cpu(), model.sample_rate, strategy="loudness")
|
| 124 |
+
```
|
| 125 |
+
|
| 126 |
+
## Model details
|
| 127 |
+
|
| 128 |
+
**Organization developing the model:** The FAIR team of Meta AI.
|
| 129 |
+
|
| 130 |
+
**Model date:** MusicGen was trained between April 2023 and May 2023.
|
| 131 |
+
|
| 132 |
+
**Model version:** This is the version 1 of the model.
|
| 133 |
+
|
| 134 |
+
**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.
|
| 135 |
+
|
| 136 |
+
**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).
|
| 137 |
+
|
| 138 |
+
**Citation details:**
|
| 139 |
+
```
|
| 140 |
+
@misc{copet2023simple,
|
| 141 |
+
title={Simple and Controllable Music Generation},
|
| 142 |
+
author={Jade Copet and Felix Kreuk and Itai Gat and Tal Remez and David Kant and Gabriel Synnaeve and Yossi Adi and Alexandre Défossez},
|
| 143 |
+
year={2023},
|
| 144 |
+
eprint={2306.05284},
|
| 145 |
+
archivePrefix={arXiv},
|
| 146 |
+
primaryClass={cs.SD}
|
| 147 |
+
}
|
| 148 |
+
```
|
| 149 |
+
|
| 150 |
+
**License:** Code is released under MIT, model weights are released under CC-BY-NC 4.0.
|
| 151 |
+
|
| 152 |
+
**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.
|
| 153 |
+
|
| 154 |
+
## Intended use
|
| 155 |
+
**Primary intended use:** The primary use of MusicGen is research on AI-based music generation, including:
|
| 156 |
+
|
| 157 |
+
- Research efforts, such as probing and better understanding the limitations of generative models to further improve the state of science
|
| 158 |
+
- Generation of music guided by text or melody to understand current abilities of generative AI models by machine learning amateurs
|
| 159 |
+
|
| 160 |
+
**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.
|
| 161 |
+
|
| 162 |
+
**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.
|
| 163 |
+
|
| 164 |
+
## Metrics
|
| 165 |
+
|
| 166 |
+
**Models performance measures:** We used the following objective measure to evaluate the model on a standard music benchmark:
|
| 167 |
+
|
| 168 |
+
- Frechet Audio Distance computed on features extracted from a pre-trained audio classifier (VGGish)
|
| 169 |
+
- Kullback-Leibler Divergence on label distributions extracted from a pre-trained audio classifier (PaSST)
|
| 170 |
+
- CLAP Score between audio embedding and text embedding extracted from a pre-trained CLAP model
|
| 171 |
+
|
| 172 |
+
Additionally, we run qualitative studies with human participants, evaluating the performance of the model with the following axes:
|
| 173 |
+
|
| 174 |
+
- Overall quality of the music samples;
|
| 175 |
+
- Text relevance to the provided text input;
|
| 176 |
+
- Adherence to the melody for melody-guided music generation.
|
| 177 |
+
|
| 178 |
+
More details on performance measures and human studies can be found in the paper.
|
| 179 |
+
|
| 180 |
+
**Decision thresholds:** Not applicable.
|
| 181 |
+
|
| 182 |
+
## Evaluation datasets
|
| 183 |
+
|
| 184 |
+
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.
|
| 185 |
+
|
| 186 |
+
## Training datasets
|
| 187 |
+
|
| 188 |
+
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.
|
| 189 |
+
|
| 190 |
+
## Evaluation results
|
| 191 |
+
|
| 192 |
+
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.
|
| 193 |
+
|
| 194 |
+
| Model | Frechet Audio Distance | KLD | Text Consistency | Chroma Cosine Similarity |
|
| 195 |
+
|---|---|---|---|---|
|
| 196 |
+
| facebook/musicgen-small | 4.88 | 1.42 | 0.27 | - |
|
| 197 |
+
| facebook/musicgen-medium | 5.14 | 1.38 | 0.28 | - |
|
| 198 |
+
| **facebook/musicgen-large** | 5.48 | 1.37 | 0.28 | - |
|
| 199 |
+
| facebook/musicgen-melody | 4.93 | 1.41 | 0.27 | 0.44 |
|
| 200 |
+
|
| 201 |
+
More information can be found in the paper [Simple and Controllable Music Generation](https://arxiv.org/abs/2306.05284), in the Results section.
|
| 202 |
+
|
| 203 |
+
## Limitations and biases
|
| 204 |
+
|
| 205 |
+
**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.
|
| 206 |
+
|
| 207 |
+
**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).
|
| 208 |
+
|
| 209 |
+
**Limitations:**
|
| 210 |
+
|
| 211 |
+
- The model is not able to generate realistic vocals.
|
| 212 |
+
- The model has been trained with English descriptions and will not perform as well in other languages.
|
| 213 |
+
- The model does not perform equally well for all music styles and cultures.
|
| 214 |
+
- The model sometimes generates end of songs, collapsing to silence.
|
| 215 |
+
- It is sometimes difficult to assess what types of text descriptions provide the best generations. Prompt engineering may be required to obtain satisfying results.
|
| 216 |
+
|
| 217 |
+
**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.
|
| 218 |
+
|
| 219 |
+
**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.
|
| 220 |
+
|
| 221 |
+
**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
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37d256b525d4117f8bbf790ab448a8e9f4746cd401900fe1ae72e154b1513a30
|
| 3 |
+
size 236001935
|
config.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_commit_hash": null,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MusicgenForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"audio_encoder": {
|
| 7 |
+
"_name_or_path": "facebook/encodec_32khz",
|
| 8 |
+
"add_cross_attention": false,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"EncodecModel"
|
| 11 |
+
],
|
| 12 |
+
"audio_channels": 1,
|
| 13 |
+
"bad_words_ids": null,
|
| 14 |
+
"begin_suppress_tokens": null,
|
| 15 |
+
"bos_token_id": null,
|
| 16 |
+
"chunk_length_s": null,
|
| 17 |
+
"chunk_size_feed_forward": 0,
|
| 18 |
+
"codebook_dim": 128,
|
| 19 |
+
"codebook_size": 2048,
|
| 20 |
+
"compress": 2,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"dilation_growth_rate": 2,
|
| 24 |
+
"diversity_penalty": 0.0,
|
| 25 |
+
"do_sample": false,
|
| 26 |
+
"early_stopping": false,
|
| 27 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 28 |
+
"eos_token_id": null,
|
| 29 |
+
"exponential_decay_length_penalty": null,
|
| 30 |
+
"finetuning_task": null,
|
| 31 |
+
"forced_bos_token_id": null,
|
| 32 |
+
"forced_eos_token_id": null,
|
| 33 |
+
"hidden_size": 128,
|
| 34 |
+
"id2label": {
|
| 35 |
+
"0": "LABEL_0",
|
| 36 |
+
"1": "LABEL_1"
|
| 37 |
+
},
|
| 38 |
+
"is_decoder": false,
|
| 39 |
+
"is_encoder_decoder": false,
|
| 40 |
+
"kernel_size": 7,
|
| 41 |
+
"label2id": {
|
| 42 |
+
"LABEL_0": 0,
|
| 43 |
+
"LABEL_1": 1
|
| 44 |
+
},
|
| 45 |
+
"last_kernel_size": 7,
|
| 46 |
+
"length_penalty": 1.0,
|
| 47 |
+
"max_length": 20,
|
| 48 |
+
"min_length": 0,
|
| 49 |
+
"model_type": "encodec",
|
| 50 |
+
"no_repeat_ngram_size": 0,
|
| 51 |
+
"norm_type": "weight_norm",
|
| 52 |
+
"normalize": false,
|
| 53 |
+
"num_beam_groups": 1,
|
| 54 |
+
"num_beams": 1,
|
| 55 |
+
"num_filters": 64,
|
| 56 |
+
"num_lstm_layers": 2,
|
| 57 |
+
"num_residual_layers": 1,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"overlap": null,
|
| 63 |
+
"pad_mode": "reflect",
|
| 64 |
+
"pad_token_id": null,
|
| 65 |
+
"prefix": null,
|
| 66 |
+
"problem_type": null,
|
| 67 |
+
"pruned_heads": {},
|
| 68 |
+
"remove_invalid_values": false,
|
| 69 |
+
"repetition_penalty": 1.0,
|
| 70 |
+
"residual_kernel_size": 3,
|
| 71 |
+
"return_dict": true,
|
| 72 |
+
"return_dict_in_generate": false,
|
| 73 |
+
"sampling_rate": 32000,
|
| 74 |
+
"sep_token_id": null,
|
| 75 |
+
"suppress_tokens": null,
|
| 76 |
+
"target_bandwidths": [
|
| 77 |
+
2.2
|
| 78 |
+
],
|
| 79 |
+
"task_specific_params": null,
|
| 80 |
+
"temperature": 1.0,
|
| 81 |
+
"tf_legacy_loss": false,
|
| 82 |
+
"tie_encoder_decoder": false,
|
| 83 |
+
"tie_word_embeddings": true,
|
| 84 |
+
"tokenizer_class": null,
|
| 85 |
+
"top_k": 50,
|
| 86 |
+
"top_p": 1.0,
|
| 87 |
+
"torch_dtype": "float32",
|
| 88 |
+
"torchscript": false,
|
| 89 |
+
"transformers_version": "4.31.0.dev0",
|
| 90 |
+
"trim_right_ratio": 1.0,
|
| 91 |
+
"typical_p": 1.0,
|
| 92 |
+
"upsampling_ratios": [
|
| 93 |
+
8,
|
| 94 |
+
5,
|
| 95 |
+
4,
|
| 96 |
+
4
|
| 97 |
+
],
|
| 98 |
+
"use_bfloat16": false,
|
| 99 |
+
"use_causal_conv": false,
|
| 100 |
+
"use_conv_shortcut": false
|
| 101 |
+
},
|
| 102 |
+
"decoder": {
|
| 103 |
+
"_name_or_path": "",
|
| 104 |
+
"activation_dropout": 0.0,
|
| 105 |
+
"activation_function": "gelu",
|
| 106 |
+
"add_cross_attention": false,
|
| 107 |
+
"architectures": null,
|
| 108 |
+
"attention_dropout": 0.0,
|
| 109 |
+
"bad_words_ids": null,
|
| 110 |
+
"begin_suppress_tokens": null,
|
| 111 |
+
"bos_token_id": 2048,
|
| 112 |
+
"chunk_size_feed_forward": 0,
|
| 113 |
+
"classifier_dropout": 0.0,
|
| 114 |
+
"cross_attention_hidden_size": null,
|
| 115 |
+
"decoder_start_token_id": null,
|
| 116 |
+
"diversity_penalty": 0.0,
|
| 117 |
+
"do_sample": false,
|
| 118 |
+
"dropout": 0.1,
|
| 119 |
+
"early_stopping": false,
|
| 120 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 121 |
+
"eos_token_id": null,
|
| 122 |
+
"exponential_decay_length_penalty": null,
|
| 123 |
+
"ffn_dim": 8192,
|
| 124 |
+
"finetuning_task": null,
|
| 125 |
+
"forced_bos_token_id": null,
|
| 126 |
+
"forced_eos_token_id": null,
|
| 127 |
+
"hidden_size": 2048,
|
| 128 |
+
"id2label": {
|
| 129 |
+
"0": "LABEL_0",
|
| 130 |
+
"1": "LABEL_1"
|
| 131 |
+
},
|
| 132 |
+
"initializer_factor": 0.02,
|
| 133 |
+
"is_decoder": false,
|
| 134 |
+
"is_encoder_decoder": false,
|
| 135 |
+
"label2id": {
|
| 136 |
+
"LABEL_0": 0,
|
| 137 |
+
"LABEL_1": 1
|
| 138 |
+
},
|
| 139 |
+
"layerdrop": 0.0,
|
| 140 |
+
"length_penalty": 1.0,
|
| 141 |
+
"max_length": 20,
|
| 142 |
+
"max_position_embeddings": 2048,
|
| 143 |
+
"min_length": 0,
|
| 144 |
+
"model_type": "musicgen_decoder",
|
| 145 |
+
"no_repeat_ngram_size": 0,
|
| 146 |
+
"num_attention_heads": 32,
|
| 147 |
+
"num_beam_groups": 1,
|
| 148 |
+
"num_beams": 1,
|
| 149 |
+
"num_codebooks": 4,
|
| 150 |
+
"num_hidden_layers": 48,
|
| 151 |
+
"num_return_sequences": 1,
|
| 152 |
+
"output_attentions": false,
|
| 153 |
+
"output_hidden_states": false,
|
| 154 |
+
"output_scores": false,
|
| 155 |
+
"pad_token_id": 2048,
|
| 156 |
+
"prefix": null,
|
| 157 |
+
"problem_type": null,
|
| 158 |
+
"pruned_heads": {},
|
| 159 |
+
"remove_invalid_values": false,
|
| 160 |
+
"repetition_penalty": 1.0,
|
| 161 |
+
"return_dict": true,
|
| 162 |
+
"return_dict_in_generate": false,
|
| 163 |
+
"scale_embedding": false,
|
| 164 |
+
"sep_token_id": null,
|
| 165 |
+
"suppress_tokens": null,
|
| 166 |
+
"task_specific_params": null,
|
| 167 |
+
"temperature": 1.0,
|
| 168 |
+
"tf_legacy_loss": false,
|
| 169 |
+
"tie_encoder_decoder": false,
|
| 170 |
+
"tie_word_embeddings": false,
|
| 171 |
+
"tokenizer_class": null,
|
| 172 |
+
"top_k": 50,
|
| 173 |
+
"top_p": 1.0,
|
| 174 |
+
"torch_dtype": null,
|
| 175 |
+
"torchscript": false,
|
| 176 |
+
"transformers_version": "4.31.0.dev0",
|
| 177 |
+
"typical_p": 1.0,
|
| 178 |
+
"use_bfloat16": false,
|
| 179 |
+
"use_cache": true,
|
| 180 |
+
"vocab_size": 2048
|
| 181 |
+
},
|
| 182 |
+
"is_encoder_decoder": true,
|
| 183 |
+
"model_type": "musicgen",
|
| 184 |
+
"text_encoder": {
|
| 185 |
+
"_name_or_path": "t5-base",
|
| 186 |
+
"add_cross_attention": false,
|
| 187 |
+
"architectures": [
|
| 188 |
+
"T5ForConditionalGeneration"
|
| 189 |
+
],
|
| 190 |
+
"bad_words_ids": null,
|
| 191 |
+
"begin_suppress_tokens": null,
|
| 192 |
+
"bos_token_id": null,
|
| 193 |
+
"chunk_size_feed_forward": 0,
|
| 194 |
+
"cross_attention_hidden_size": null,
|
| 195 |
+
"d_ff": 3072,
|
| 196 |
+
"d_kv": 64,
|
| 197 |
+
"d_model": 768,
|
| 198 |
+
"decoder_start_token_id": 0,
|
| 199 |
+
"dense_act_fn": "relu",
|
| 200 |
+
"diversity_penalty": 0.0,
|
| 201 |
+
"do_sample": false,
|
| 202 |
+
"dropout_rate": 0.1,
|
| 203 |
+
"early_stopping": false,
|
| 204 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 205 |
+
"eos_token_id": 1,
|
| 206 |
+
"exponential_decay_length_penalty": null,
|
| 207 |
+
"feed_forward_proj": "relu",
|
| 208 |
+
"finetuning_task": null,
|
| 209 |
+
"forced_bos_token_id": null,
|
| 210 |
+
"forced_eos_token_id": null,
|
| 211 |
+
"id2label": {
|
| 212 |
+
"0": "LABEL_0",
|
| 213 |
+
"1": "LABEL_1"
|
| 214 |
+
},
|
| 215 |
+
"initializer_factor": 1.0,
|
| 216 |
+
"is_decoder": false,
|
| 217 |
+
"is_encoder_decoder": true,
|
| 218 |
+
"is_gated_act": false,
|
| 219 |
+
"label2id": {
|
| 220 |
+
"LABEL_0": 0,
|
| 221 |
+
"LABEL_1": 1
|
| 222 |
+
},
|
| 223 |
+
"layer_norm_epsilon": 1e-06,
|
| 224 |
+
"length_penalty": 1.0,
|
| 225 |
+
"max_length": 20,
|
| 226 |
+
"min_length": 0,
|
| 227 |
+
"model_type": "t5",
|
| 228 |
+
"n_positions": 512,
|
| 229 |
+
"no_repeat_ngram_size": 0,
|
| 230 |
+
"num_beam_groups": 1,
|
| 231 |
+
"num_beams": 1,
|
| 232 |
+
"num_decoder_layers": 12,
|
| 233 |
+
"num_heads": 12,
|
| 234 |
+
"num_layers": 12,
|
| 235 |
+
"num_return_sequences": 1,
|
| 236 |
+
"output_attentions": false,
|
| 237 |
+
"output_hidden_states": false,
|
| 238 |
+
"output_past": true,
|
| 239 |
+
"output_scores": false,
|
| 240 |
+
"pad_token_id": 0,
|
| 241 |
+
"prefix": null,
|
| 242 |
+
"problem_type": null,
|
| 243 |
+
"pruned_heads": {},
|
| 244 |
+
"relative_attention_max_distance": 128,
|
| 245 |
+
"relative_attention_num_buckets": 32,
|
| 246 |
+
"remove_invalid_values": false,
|
| 247 |
+
"repetition_penalty": 1.0,
|
| 248 |
+
"return_dict": true,
|
| 249 |
+
"return_dict_in_generate": false,
|
| 250 |
+
"sep_token_id": null,
|
| 251 |
+
"suppress_tokens": null,
|
| 252 |
+
"task_specific_params": {
|
| 253 |
+
"summarization": {
|
| 254 |
+
"early_stopping": true,
|
| 255 |
+
"length_penalty": 2.0,
|
| 256 |
+
"max_length": 200,
|
| 257 |
+
"min_length": 30,
|
| 258 |
+
"no_repeat_ngram_size": 3,
|
| 259 |
+
"num_beams": 4,
|
| 260 |
+
"prefix": "summarize: "
|
| 261 |
+
},
|
| 262 |
+
"translation_en_to_de": {
|
| 263 |
+
"early_stopping": true,
|
| 264 |
+
"max_length": 300,
|
| 265 |
+
"num_beams": 4,
|
| 266 |
+
"prefix": "translate English to German: "
|
| 267 |
+
},
|
| 268 |
+
"translation_en_to_fr": {
|
| 269 |
+
"early_stopping": true,
|
| 270 |
+
"max_length": 300,
|
| 271 |
+
"num_beams": 4,
|
| 272 |
+
"prefix": "translate English to French: "
|
| 273 |
+
},
|
| 274 |
+
"translation_en_to_ro": {
|
| 275 |
+
"early_stopping": true,
|
| 276 |
+
"max_length": 300,
|
| 277 |
+
"num_beams": 4,
|
| 278 |
+
"prefix": "translate English to Romanian: "
|
| 279 |
+
}
|
| 280 |
+
},
|
| 281 |
+
"temperature": 1.0,
|
| 282 |
+
"tf_legacy_loss": false,
|
| 283 |
+
"tie_encoder_decoder": false,
|
| 284 |
+
"tie_word_embeddings": true,
|
| 285 |
+
"tokenizer_class": null,
|
| 286 |
+
"top_k": 50,
|
| 287 |
+
"top_p": 1.0,
|
| 288 |
+
"torch_dtype": null,
|
| 289 |
+
"torchscript": false,
|
| 290 |
+
"transformers_version": "4.31.0.dev0",
|
| 291 |
+
"typical_p": 1.0,
|
| 292 |
+
"use_bfloat16": false,
|
| 293 |
+
"use_cache": true,
|
| 294 |
+
"vocab_size": 32128
|
| 295 |
+
},
|
| 296 |
+
"torch_dtype": "float32",
|
| 297 |
+
"transformers_version": null
|
| 298 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2048,
|
| 4 |
+
"decoder_start_token_id": 2048,
|
| 5 |
+
"do_sample": true,
|
| 6 |
+
"guidance_scale": 3.0,
|
| 7 |
+
"max_length": 1500,
|
| 8 |
+
"pad_token_id": 2048,
|
| 9 |
+
"transformers_version": "4.31.0.dev0"
|
| 10 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length_s": null,
|
| 3 |
+
"feature_extractor_type": "EncodecFeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"overlap": null,
|
| 6 |
+
"padding_side": "left",
|
| 7 |
+
"padding_value": 0.0,
|
| 8 |
+
"processor_class": "MusicgenProcessor",
|
| 9 |
+
"return_attention_mask": true,
|
| 10 |
+
"sampling_rate": 32000
|
| 11 |
+
}
|
pytorch_model-00001-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7ed8a0d95eff206263d1ae62955a7b8a7dab11a6b55e953887aea6ed54f85bd
|
| 3 |
+
size 9987827539
|
pytorch_model-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9923d2947297a9883404abfd4041a32cf486c763d36e00eb4f178823bf6bdac
|
| 3 |
+
size 3731608779
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,1004 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13719079192
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"audio_encoder.decoder.layers.0.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 7 |
+
"audio_encoder.decoder.layers.0.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 8 |
+
"audio_encoder.decoder.layers.0.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 9 |
+
"audio_encoder.decoder.layers.1.lstm.bias_hh_l0": "pytorch_model-00001-of-00002.bin",
|
| 10 |
+
"audio_encoder.decoder.layers.1.lstm.bias_hh_l1": "pytorch_model-00001-of-00002.bin",
|
| 11 |
+
"audio_encoder.decoder.layers.1.lstm.bias_ih_l0": "pytorch_model-00001-of-00002.bin",
|
| 12 |
+
"audio_encoder.decoder.layers.1.lstm.bias_ih_l1": "pytorch_model-00001-of-00002.bin",
|
| 13 |
+
"audio_encoder.decoder.layers.1.lstm.weight_hh_l0": "pytorch_model-00001-of-00002.bin",
|
| 14 |
+
"audio_encoder.decoder.layers.1.lstm.weight_hh_l1": "pytorch_model-00001-of-00002.bin",
|
| 15 |
+
"audio_encoder.decoder.layers.1.lstm.weight_ih_l0": "pytorch_model-00001-of-00002.bin",
|
| 16 |
+
"audio_encoder.decoder.layers.1.lstm.weight_ih_l1": "pytorch_model-00001-of-00002.bin",
|
| 17 |
+
"audio_encoder.decoder.layers.10.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 18 |
+
"audio_encoder.decoder.layers.10.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 19 |
+
"audio_encoder.decoder.layers.10.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 20 |
+
"audio_encoder.decoder.layers.10.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 21 |
+
"audio_encoder.decoder.layers.10.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 22 |
+
"audio_encoder.decoder.layers.10.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 23 |
+
"audio_encoder.decoder.layers.12.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 24 |
+
"audio_encoder.decoder.layers.12.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 25 |
+
"audio_encoder.decoder.layers.12.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 26 |
+
"audio_encoder.decoder.layers.13.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 27 |
+
"audio_encoder.decoder.layers.13.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 28 |
+
"audio_encoder.decoder.layers.13.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 29 |
+
"audio_encoder.decoder.layers.13.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 30 |
+
"audio_encoder.decoder.layers.13.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 31 |
+
"audio_encoder.decoder.layers.13.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 32 |
+
"audio_encoder.decoder.layers.15.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 33 |
+
"audio_encoder.decoder.layers.15.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 34 |
+
"audio_encoder.decoder.layers.15.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 35 |
+
"audio_encoder.decoder.layers.3.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 36 |
+
"audio_encoder.decoder.layers.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 37 |
+
"audio_encoder.decoder.layers.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 38 |
+
"audio_encoder.decoder.layers.4.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 39 |
+
"audio_encoder.decoder.layers.4.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 40 |
+
"audio_encoder.decoder.layers.4.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 41 |
+
"audio_encoder.decoder.layers.4.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 42 |
+
"audio_encoder.decoder.layers.4.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 43 |
+
"audio_encoder.decoder.layers.4.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 44 |
+
"audio_encoder.decoder.layers.6.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 45 |
+
"audio_encoder.decoder.layers.6.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 46 |
+
"audio_encoder.decoder.layers.6.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 47 |
+
"audio_encoder.decoder.layers.7.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 48 |
+
"audio_encoder.decoder.layers.7.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 49 |
+
"audio_encoder.decoder.layers.7.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 50 |
+
"audio_encoder.decoder.layers.7.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 51 |
+
"audio_encoder.decoder.layers.7.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 52 |
+
"audio_encoder.decoder.layers.7.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 53 |
+
"audio_encoder.decoder.layers.9.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 54 |
+
"audio_encoder.decoder.layers.9.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 55 |
+
"audio_encoder.decoder.layers.9.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 56 |
+
"audio_encoder.encoder.layers.0.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 57 |
+
"audio_encoder.encoder.layers.0.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 58 |
+
"audio_encoder.encoder.layers.0.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 59 |
+
"audio_encoder.encoder.layers.1.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 60 |
+
"audio_encoder.encoder.layers.1.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 61 |
+
"audio_encoder.encoder.layers.1.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 62 |
+
"audio_encoder.encoder.layers.1.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 63 |
+
"audio_encoder.encoder.layers.1.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 64 |
+
"audio_encoder.encoder.layers.1.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 65 |
+
"audio_encoder.encoder.layers.10.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 66 |
+
"audio_encoder.encoder.layers.10.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 67 |
+
"audio_encoder.encoder.layers.10.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 68 |
+
"audio_encoder.encoder.layers.10.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 69 |
+
"audio_encoder.encoder.layers.10.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 70 |
+
"audio_encoder.encoder.layers.10.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 71 |
+
"audio_encoder.encoder.layers.12.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 72 |
+
"audio_encoder.encoder.layers.12.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 73 |
+
"audio_encoder.encoder.layers.12.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 74 |
+
"audio_encoder.encoder.layers.13.lstm.bias_hh_l0": "pytorch_model-00001-of-00002.bin",
|
| 75 |
+
"audio_encoder.encoder.layers.13.lstm.bias_hh_l1": "pytorch_model-00001-of-00002.bin",
|
| 76 |
+
"audio_encoder.encoder.layers.13.lstm.bias_ih_l0": "pytorch_model-00001-of-00002.bin",
|
| 77 |
+
"audio_encoder.encoder.layers.13.lstm.bias_ih_l1": "pytorch_model-00001-of-00002.bin",
|
| 78 |
+
"audio_encoder.encoder.layers.13.lstm.weight_hh_l0": "pytorch_model-00001-of-00002.bin",
|
| 79 |
+
"audio_encoder.encoder.layers.13.lstm.weight_hh_l1": "pytorch_model-00001-of-00002.bin",
|
| 80 |
+
"audio_encoder.encoder.layers.13.lstm.weight_ih_l0": "pytorch_model-00001-of-00002.bin",
|
| 81 |
+
"audio_encoder.encoder.layers.13.lstm.weight_ih_l1": "pytorch_model-00001-of-00002.bin",
|
| 82 |
+
"audio_encoder.encoder.layers.15.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 83 |
+
"audio_encoder.encoder.layers.15.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 84 |
+
"audio_encoder.encoder.layers.15.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 85 |
+
"audio_encoder.encoder.layers.3.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 86 |
+
"audio_encoder.encoder.layers.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 87 |
+
"audio_encoder.encoder.layers.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 88 |
+
"audio_encoder.encoder.layers.4.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 89 |
+
"audio_encoder.encoder.layers.4.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 90 |
+
"audio_encoder.encoder.layers.4.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 91 |
+
"audio_encoder.encoder.layers.4.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 92 |
+
"audio_encoder.encoder.layers.4.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 93 |
+
"audio_encoder.encoder.layers.4.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 94 |
+
"audio_encoder.encoder.layers.6.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 95 |
+
"audio_encoder.encoder.layers.6.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 96 |
+
"audio_encoder.encoder.layers.6.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 97 |
+
"audio_encoder.encoder.layers.7.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 98 |
+
"audio_encoder.encoder.layers.7.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 99 |
+
"audio_encoder.encoder.layers.7.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 100 |
+
"audio_encoder.encoder.layers.7.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 101 |
+
"audio_encoder.encoder.layers.7.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 102 |
+
"audio_encoder.encoder.layers.7.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 103 |
+
"audio_encoder.encoder.layers.9.conv.bias": "pytorch_model-00001-of-00002.bin",
|
| 104 |
+
"audio_encoder.encoder.layers.9.conv.weight_g": "pytorch_model-00001-of-00002.bin",
|
| 105 |
+
"audio_encoder.encoder.layers.9.conv.weight_v": "pytorch_model-00001-of-00002.bin",
|
| 106 |
+
"audio_encoder.quantizer.layers.0.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
|
| 107 |
+
"audio_encoder.quantizer.layers.0.codebook.embed": "pytorch_model-00001-of-00002.bin",
|
| 108 |
+
"audio_encoder.quantizer.layers.0.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
|
| 109 |
+
"audio_encoder.quantizer.layers.0.codebook.inited": "pytorch_model-00001-of-00002.bin",
|
| 110 |
+
"audio_encoder.quantizer.layers.1.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
|
| 111 |
+
"audio_encoder.quantizer.layers.1.codebook.embed": "pytorch_model-00001-of-00002.bin",
|
| 112 |
+
"audio_encoder.quantizer.layers.1.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
|
| 113 |
+
"audio_encoder.quantizer.layers.1.codebook.inited": "pytorch_model-00001-of-00002.bin",
|
| 114 |
+
"audio_encoder.quantizer.layers.2.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
|
| 115 |
+
"audio_encoder.quantizer.layers.2.codebook.embed": "pytorch_model-00001-of-00002.bin",
|
| 116 |
+
"audio_encoder.quantizer.layers.2.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
|
| 117 |
+
"audio_encoder.quantizer.layers.2.codebook.inited": "pytorch_model-00001-of-00002.bin",
|
| 118 |
+
"audio_encoder.quantizer.layers.3.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
|
| 119 |
+
"audio_encoder.quantizer.layers.3.codebook.embed": "pytorch_model-00001-of-00002.bin",
|
| 120 |
+
"audio_encoder.quantizer.layers.3.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
|
| 121 |
+
"audio_encoder.quantizer.layers.3.codebook.inited": "pytorch_model-00001-of-00002.bin",
|
| 122 |
+
"decoder.lm_heads.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 123 |
+
"decoder.lm_heads.1.weight": "pytorch_model-00002-of-00002.bin",
|
| 124 |
+
"decoder.lm_heads.2.weight": "pytorch_model-00002-of-00002.bin",
|
| 125 |
+
"decoder.lm_heads.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 126 |
+
"decoder.model.decoder.embed_positions.weights": "pytorch_model-00001-of-00002.bin",
|
| 127 |
+
"decoder.model.decoder.embed_tokens.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 128 |
+
"decoder.model.decoder.embed_tokens.1.weight": "pytorch_model-00001-of-00002.bin",
|
| 129 |
+
"decoder.model.decoder.embed_tokens.2.weight": "pytorch_model-00001-of-00002.bin",
|
| 130 |
+
"decoder.model.decoder.embed_tokens.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 131 |
+
"decoder.model.decoder.layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 132 |
+
"decoder.model.decoder.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 133 |
+
"decoder.model.decoder.layers.0.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 134 |
+
"decoder.model.decoder.layers.0.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 135 |
+
"decoder.model.decoder.layers.0.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 136 |
+
"decoder.model.decoder.layers.0.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 137 |
+
"decoder.model.decoder.layers.0.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 138 |
+
"decoder.model.decoder.layers.0.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 139 |
+
"decoder.model.decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 140 |
+
"decoder.model.decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 141 |
+
"decoder.model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 142 |
+
"decoder.model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 143 |
+
"decoder.model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 144 |
+
"decoder.model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 145 |
+
"decoder.model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 146 |
+
"decoder.model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 147 |
+
"decoder.model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 148 |
+
"decoder.model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 149 |
+
"decoder.model.decoder.layers.1.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 150 |
+
"decoder.model.decoder.layers.1.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 151 |
+
"decoder.model.decoder.layers.1.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 152 |
+
"decoder.model.decoder.layers.1.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 153 |
+
"decoder.model.decoder.layers.1.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 154 |
+
"decoder.model.decoder.layers.1.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 155 |
+
"decoder.model.decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 156 |
+
"decoder.model.decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 157 |
+
"decoder.model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 158 |
+
"decoder.model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 159 |
+
"decoder.model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 160 |
+
"decoder.model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 161 |
+
"decoder.model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 162 |
+
"decoder.model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 163 |
+
"decoder.model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 164 |
+
"decoder.model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 165 |
+
"decoder.model.decoder.layers.10.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 166 |
+
"decoder.model.decoder.layers.10.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 167 |
+
"decoder.model.decoder.layers.10.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 168 |
+
"decoder.model.decoder.layers.10.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 169 |
+
"decoder.model.decoder.layers.10.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 170 |
+
"decoder.model.decoder.layers.10.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 171 |
+
"decoder.model.decoder.layers.10.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 172 |
+
"decoder.model.decoder.layers.10.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 173 |
+
"decoder.model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 174 |
+
"decoder.model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 175 |
+
"decoder.model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 176 |
+
"decoder.model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 177 |
+
"decoder.model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 178 |
+
"decoder.model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 179 |
+
"decoder.model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 180 |
+
"decoder.model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 181 |
+
"decoder.model.decoder.layers.11.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 182 |
+
"decoder.model.decoder.layers.11.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 183 |
+
"decoder.model.decoder.layers.11.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 184 |
+
"decoder.model.decoder.layers.11.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 185 |
+
"decoder.model.decoder.layers.11.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 186 |
+
"decoder.model.decoder.layers.11.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 187 |
+
"decoder.model.decoder.layers.11.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 188 |
+
"decoder.model.decoder.layers.11.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 189 |
+
"decoder.model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 190 |
+
"decoder.model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 191 |
+
"decoder.model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 192 |
+
"decoder.model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 193 |
+
"decoder.model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 194 |
+
"decoder.model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 195 |
+
"decoder.model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 196 |
+
"decoder.model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 197 |
+
"decoder.model.decoder.layers.12.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 198 |
+
"decoder.model.decoder.layers.12.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 199 |
+
"decoder.model.decoder.layers.12.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 200 |
+
"decoder.model.decoder.layers.12.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 201 |
+
"decoder.model.decoder.layers.12.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 202 |
+
"decoder.model.decoder.layers.12.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 203 |
+
"decoder.model.decoder.layers.12.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 204 |
+
"decoder.model.decoder.layers.12.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 205 |
+
"decoder.model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 206 |
+
"decoder.model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 207 |
+
"decoder.model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 208 |
+
"decoder.model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 209 |
+
"decoder.model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 210 |
+
"decoder.model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 211 |
+
"decoder.model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 212 |
+
"decoder.model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 213 |
+
"decoder.model.decoder.layers.13.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 214 |
+
"decoder.model.decoder.layers.13.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 215 |
+
"decoder.model.decoder.layers.13.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 216 |
+
"decoder.model.decoder.layers.13.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 217 |
+
"decoder.model.decoder.layers.13.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 218 |
+
"decoder.model.decoder.layers.13.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 219 |
+
"decoder.model.decoder.layers.13.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 220 |
+
"decoder.model.decoder.layers.13.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 221 |
+
"decoder.model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 222 |
+
"decoder.model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 223 |
+
"decoder.model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 224 |
+
"decoder.model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 225 |
+
"decoder.model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 226 |
+
"decoder.model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 227 |
+
"decoder.model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 228 |
+
"decoder.model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 229 |
+
"decoder.model.decoder.layers.14.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 230 |
+
"decoder.model.decoder.layers.14.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 231 |
+
"decoder.model.decoder.layers.14.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 232 |
+
"decoder.model.decoder.layers.14.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 233 |
+
"decoder.model.decoder.layers.14.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 234 |
+
"decoder.model.decoder.layers.14.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 235 |
+
"decoder.model.decoder.layers.14.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 236 |
+
"decoder.model.decoder.layers.14.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 237 |
+
"decoder.model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 238 |
+
"decoder.model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 239 |
+
"decoder.model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 240 |
+
"decoder.model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 241 |
+
"decoder.model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 242 |
+
"decoder.model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 243 |
+
"decoder.model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 244 |
+
"decoder.model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 245 |
+
"decoder.model.decoder.layers.15.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 246 |
+
"decoder.model.decoder.layers.15.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 247 |
+
"decoder.model.decoder.layers.15.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 248 |
+
"decoder.model.decoder.layers.15.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 249 |
+
"decoder.model.decoder.layers.15.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 250 |
+
"decoder.model.decoder.layers.15.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 251 |
+
"decoder.model.decoder.layers.15.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 252 |
+
"decoder.model.decoder.layers.15.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 253 |
+
"decoder.model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 254 |
+
"decoder.model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 255 |
+
"decoder.model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 256 |
+
"decoder.model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 257 |
+
"decoder.model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 258 |
+
"decoder.model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 259 |
+
"decoder.model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 260 |
+
"decoder.model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 261 |
+
"decoder.model.decoder.layers.16.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 262 |
+
"decoder.model.decoder.layers.16.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 263 |
+
"decoder.model.decoder.layers.16.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 264 |
+
"decoder.model.decoder.layers.16.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 265 |
+
"decoder.model.decoder.layers.16.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 266 |
+
"decoder.model.decoder.layers.16.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 267 |
+
"decoder.model.decoder.layers.16.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 268 |
+
"decoder.model.decoder.layers.16.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 269 |
+
"decoder.model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 270 |
+
"decoder.model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 271 |
+
"decoder.model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 272 |
+
"decoder.model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 273 |
+
"decoder.model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 274 |
+
"decoder.model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 275 |
+
"decoder.model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 276 |
+
"decoder.model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 277 |
+
"decoder.model.decoder.layers.17.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 278 |
+
"decoder.model.decoder.layers.17.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 279 |
+
"decoder.model.decoder.layers.17.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 280 |
+
"decoder.model.decoder.layers.17.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 281 |
+
"decoder.model.decoder.layers.17.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 282 |
+
"decoder.model.decoder.layers.17.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 283 |
+
"decoder.model.decoder.layers.17.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 284 |
+
"decoder.model.decoder.layers.17.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 285 |
+
"decoder.model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 286 |
+
"decoder.model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 287 |
+
"decoder.model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 288 |
+
"decoder.model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 289 |
+
"decoder.model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 290 |
+
"decoder.model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 291 |
+
"decoder.model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 292 |
+
"decoder.model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 293 |
+
"decoder.model.decoder.layers.18.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 294 |
+
"decoder.model.decoder.layers.18.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 295 |
+
"decoder.model.decoder.layers.18.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 296 |
+
"decoder.model.decoder.layers.18.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 297 |
+
"decoder.model.decoder.layers.18.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 298 |
+
"decoder.model.decoder.layers.18.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 299 |
+
"decoder.model.decoder.layers.18.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 300 |
+
"decoder.model.decoder.layers.18.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 301 |
+
"decoder.model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 302 |
+
"decoder.model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 303 |
+
"decoder.model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 304 |
+
"decoder.model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 305 |
+
"decoder.model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 306 |
+
"decoder.model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 307 |
+
"decoder.model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 308 |
+
"decoder.model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 309 |
+
"decoder.model.decoder.layers.19.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 310 |
+
"decoder.model.decoder.layers.19.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 311 |
+
"decoder.model.decoder.layers.19.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 312 |
+
"decoder.model.decoder.layers.19.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 313 |
+
"decoder.model.decoder.layers.19.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 314 |
+
"decoder.model.decoder.layers.19.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 315 |
+
"decoder.model.decoder.layers.19.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 316 |
+
"decoder.model.decoder.layers.19.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 317 |
+
"decoder.model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 318 |
+
"decoder.model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 319 |
+
"decoder.model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 320 |
+
"decoder.model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 321 |
+
"decoder.model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 322 |
+
"decoder.model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 323 |
+
"decoder.model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 324 |
+
"decoder.model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 325 |
+
"decoder.model.decoder.layers.2.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 326 |
+
"decoder.model.decoder.layers.2.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 327 |
+
"decoder.model.decoder.layers.2.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 328 |
+
"decoder.model.decoder.layers.2.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 329 |
+
"decoder.model.decoder.layers.2.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 330 |
+
"decoder.model.decoder.layers.2.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 331 |
+
"decoder.model.decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 332 |
+
"decoder.model.decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 333 |
+
"decoder.model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 334 |
+
"decoder.model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 335 |
+
"decoder.model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 336 |
+
"decoder.model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 337 |
+
"decoder.model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 338 |
+
"decoder.model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 339 |
+
"decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 340 |
+
"decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 341 |
+
"decoder.model.decoder.layers.20.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 342 |
+
"decoder.model.decoder.layers.20.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 343 |
+
"decoder.model.decoder.layers.20.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 344 |
+
"decoder.model.decoder.layers.20.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 345 |
+
"decoder.model.decoder.layers.20.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 346 |
+
"decoder.model.decoder.layers.20.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 347 |
+
"decoder.model.decoder.layers.20.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 348 |
+
"decoder.model.decoder.layers.20.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 349 |
+
"decoder.model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 350 |
+
"decoder.model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 351 |
+
"decoder.model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 352 |
+
"decoder.model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 353 |
+
"decoder.model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 354 |
+
"decoder.model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 355 |
+
"decoder.model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 356 |
+
"decoder.model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 357 |
+
"decoder.model.decoder.layers.21.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 358 |
+
"decoder.model.decoder.layers.21.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 359 |
+
"decoder.model.decoder.layers.21.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 360 |
+
"decoder.model.decoder.layers.21.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 361 |
+
"decoder.model.decoder.layers.21.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 362 |
+
"decoder.model.decoder.layers.21.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 363 |
+
"decoder.model.decoder.layers.21.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 364 |
+
"decoder.model.decoder.layers.21.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 365 |
+
"decoder.model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 366 |
+
"decoder.model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 367 |
+
"decoder.model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 368 |
+
"decoder.model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 369 |
+
"decoder.model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 370 |
+
"decoder.model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 371 |
+
"decoder.model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 372 |
+
"decoder.model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 373 |
+
"decoder.model.decoder.layers.22.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 374 |
+
"decoder.model.decoder.layers.22.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 375 |
+
"decoder.model.decoder.layers.22.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 376 |
+
"decoder.model.decoder.layers.22.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 377 |
+
"decoder.model.decoder.layers.22.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 378 |
+
"decoder.model.decoder.layers.22.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 379 |
+
"decoder.model.decoder.layers.22.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 380 |
+
"decoder.model.decoder.layers.22.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 381 |
+
"decoder.model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 382 |
+
"decoder.model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 383 |
+
"decoder.model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 384 |
+
"decoder.model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 385 |
+
"decoder.model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 386 |
+
"decoder.model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 387 |
+
"decoder.model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 388 |
+
"decoder.model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 389 |
+
"decoder.model.decoder.layers.23.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 390 |
+
"decoder.model.decoder.layers.23.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 391 |
+
"decoder.model.decoder.layers.23.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 392 |
+
"decoder.model.decoder.layers.23.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 393 |
+
"decoder.model.decoder.layers.23.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 394 |
+
"decoder.model.decoder.layers.23.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 395 |
+
"decoder.model.decoder.layers.23.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 396 |
+
"decoder.model.decoder.layers.23.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 397 |
+
"decoder.model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 398 |
+
"decoder.model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 399 |
+
"decoder.model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 400 |
+
"decoder.model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 401 |
+
"decoder.model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 402 |
+
"decoder.model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 403 |
+
"decoder.model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 404 |
+
"decoder.model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 405 |
+
"decoder.model.decoder.layers.24.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 406 |
+
"decoder.model.decoder.layers.24.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 407 |
+
"decoder.model.decoder.layers.24.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 408 |
+
"decoder.model.decoder.layers.24.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 409 |
+
"decoder.model.decoder.layers.24.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 410 |
+
"decoder.model.decoder.layers.24.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 411 |
+
"decoder.model.decoder.layers.24.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 412 |
+
"decoder.model.decoder.layers.24.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 413 |
+
"decoder.model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 414 |
+
"decoder.model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 415 |
+
"decoder.model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 416 |
+
"decoder.model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 417 |
+
"decoder.model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 418 |
+
"decoder.model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 419 |
+
"decoder.model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 420 |
+
"decoder.model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 421 |
+
"decoder.model.decoder.layers.25.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 422 |
+
"decoder.model.decoder.layers.25.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 423 |
+
"decoder.model.decoder.layers.25.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 424 |
+
"decoder.model.decoder.layers.25.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 425 |
+
"decoder.model.decoder.layers.25.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 426 |
+
"decoder.model.decoder.layers.25.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 427 |
+
"decoder.model.decoder.layers.25.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 428 |
+
"decoder.model.decoder.layers.25.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 429 |
+
"decoder.model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 430 |
+
"decoder.model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 431 |
+
"decoder.model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 432 |
+
"decoder.model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 433 |
+
"decoder.model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 434 |
+
"decoder.model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 435 |
+
"decoder.model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 436 |
+
"decoder.model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 437 |
+
"decoder.model.decoder.layers.26.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 438 |
+
"decoder.model.decoder.layers.26.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 439 |
+
"decoder.model.decoder.layers.26.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 440 |
+
"decoder.model.decoder.layers.26.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 441 |
+
"decoder.model.decoder.layers.26.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 442 |
+
"decoder.model.decoder.layers.26.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 443 |
+
"decoder.model.decoder.layers.26.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 444 |
+
"decoder.model.decoder.layers.26.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 445 |
+
"decoder.model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 446 |
+
"decoder.model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 447 |
+
"decoder.model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 448 |
+
"decoder.model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 449 |
+
"decoder.model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 450 |
+
"decoder.model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 451 |
+
"decoder.model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 452 |
+
"decoder.model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 453 |
+
"decoder.model.decoder.layers.27.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 454 |
+
"decoder.model.decoder.layers.27.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 455 |
+
"decoder.model.decoder.layers.27.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 456 |
+
"decoder.model.decoder.layers.27.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 457 |
+
"decoder.model.decoder.layers.27.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 458 |
+
"decoder.model.decoder.layers.27.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 459 |
+
"decoder.model.decoder.layers.27.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 460 |
+
"decoder.model.decoder.layers.27.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 461 |
+
"decoder.model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 462 |
+
"decoder.model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 463 |
+
"decoder.model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 464 |
+
"decoder.model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 465 |
+
"decoder.model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 466 |
+
"decoder.model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 467 |
+
"decoder.model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 468 |
+
"decoder.model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 469 |
+
"decoder.model.decoder.layers.28.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 470 |
+
"decoder.model.decoder.layers.28.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 471 |
+
"decoder.model.decoder.layers.28.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 472 |
+
"decoder.model.decoder.layers.28.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 473 |
+
"decoder.model.decoder.layers.28.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 474 |
+
"decoder.model.decoder.layers.28.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 475 |
+
"decoder.model.decoder.layers.28.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 476 |
+
"decoder.model.decoder.layers.28.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 477 |
+
"decoder.model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 478 |
+
"decoder.model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 479 |
+
"decoder.model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 480 |
+
"decoder.model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 481 |
+
"decoder.model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 482 |
+
"decoder.model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 483 |
+
"decoder.model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 484 |
+
"decoder.model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 485 |
+
"decoder.model.decoder.layers.29.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 486 |
+
"decoder.model.decoder.layers.29.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 487 |
+
"decoder.model.decoder.layers.29.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 488 |
+
"decoder.model.decoder.layers.29.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 489 |
+
"decoder.model.decoder.layers.29.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 490 |
+
"decoder.model.decoder.layers.29.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 491 |
+
"decoder.model.decoder.layers.29.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 492 |
+
"decoder.model.decoder.layers.29.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 493 |
+
"decoder.model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 494 |
+
"decoder.model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 495 |
+
"decoder.model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 496 |
+
"decoder.model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 497 |
+
"decoder.model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 498 |
+
"decoder.model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 499 |
+
"decoder.model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 500 |
+
"decoder.model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 501 |
+
"decoder.model.decoder.layers.3.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 502 |
+
"decoder.model.decoder.layers.3.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 503 |
+
"decoder.model.decoder.layers.3.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 504 |
+
"decoder.model.decoder.layers.3.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 505 |
+
"decoder.model.decoder.layers.3.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 506 |
+
"decoder.model.decoder.layers.3.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 507 |
+
"decoder.model.decoder.layers.3.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 508 |
+
"decoder.model.decoder.layers.3.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 509 |
+
"decoder.model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 510 |
+
"decoder.model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 511 |
+
"decoder.model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 512 |
+
"decoder.model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 513 |
+
"decoder.model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 514 |
+
"decoder.model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 515 |
+
"decoder.model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 516 |
+
"decoder.model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 517 |
+
"decoder.model.decoder.layers.30.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 518 |
+
"decoder.model.decoder.layers.30.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 519 |
+
"decoder.model.decoder.layers.30.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 520 |
+
"decoder.model.decoder.layers.30.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 521 |
+
"decoder.model.decoder.layers.30.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 522 |
+
"decoder.model.decoder.layers.30.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 523 |
+
"decoder.model.decoder.layers.30.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 524 |
+
"decoder.model.decoder.layers.30.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 525 |
+
"decoder.model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 526 |
+
"decoder.model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 527 |
+
"decoder.model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 528 |
+
"decoder.model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 529 |
+
"decoder.model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 530 |
+
"decoder.model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 531 |
+
"decoder.model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 532 |
+
"decoder.model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 533 |
+
"decoder.model.decoder.layers.31.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 534 |
+
"decoder.model.decoder.layers.31.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 535 |
+
"decoder.model.decoder.layers.31.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 536 |
+
"decoder.model.decoder.layers.31.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 537 |
+
"decoder.model.decoder.layers.31.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 538 |
+
"decoder.model.decoder.layers.31.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 539 |
+
"decoder.model.decoder.layers.31.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 540 |
+
"decoder.model.decoder.layers.31.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 541 |
+
"decoder.model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 542 |
+
"decoder.model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 543 |
+
"decoder.model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 544 |
+
"decoder.model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 545 |
+
"decoder.model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 546 |
+
"decoder.model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 547 |
+
"decoder.model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 548 |
+
"decoder.model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 549 |
+
"decoder.model.decoder.layers.32.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 550 |
+
"decoder.model.decoder.layers.32.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 551 |
+
"decoder.model.decoder.layers.32.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 552 |
+
"decoder.model.decoder.layers.32.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 553 |
+
"decoder.model.decoder.layers.32.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 554 |
+
"decoder.model.decoder.layers.32.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 555 |
+
"decoder.model.decoder.layers.32.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 556 |
+
"decoder.model.decoder.layers.32.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 557 |
+
"decoder.model.decoder.layers.32.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 558 |
+
"decoder.model.decoder.layers.32.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 559 |
+
"decoder.model.decoder.layers.32.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 560 |
+
"decoder.model.decoder.layers.32.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 561 |
+
"decoder.model.decoder.layers.32.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 562 |
+
"decoder.model.decoder.layers.32.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 563 |
+
"decoder.model.decoder.layers.32.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 564 |
+
"decoder.model.decoder.layers.32.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 565 |
+
"decoder.model.decoder.layers.33.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 566 |
+
"decoder.model.decoder.layers.33.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 567 |
+
"decoder.model.decoder.layers.33.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 568 |
+
"decoder.model.decoder.layers.33.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 569 |
+
"decoder.model.decoder.layers.33.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 570 |
+
"decoder.model.decoder.layers.33.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 571 |
+
"decoder.model.decoder.layers.33.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 572 |
+
"decoder.model.decoder.layers.33.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 573 |
+
"decoder.model.decoder.layers.33.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 574 |
+
"decoder.model.decoder.layers.33.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 575 |
+
"decoder.model.decoder.layers.33.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 576 |
+
"decoder.model.decoder.layers.33.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 577 |
+
"decoder.model.decoder.layers.33.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 578 |
+
"decoder.model.decoder.layers.33.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 579 |
+
"decoder.model.decoder.layers.33.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 580 |
+
"decoder.model.decoder.layers.33.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 581 |
+
"decoder.model.decoder.layers.34.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 582 |
+
"decoder.model.decoder.layers.34.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 583 |
+
"decoder.model.decoder.layers.34.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 584 |
+
"decoder.model.decoder.layers.34.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 585 |
+
"decoder.model.decoder.layers.34.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 586 |
+
"decoder.model.decoder.layers.34.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 587 |
+
"decoder.model.decoder.layers.34.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 588 |
+
"decoder.model.decoder.layers.34.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 589 |
+
"decoder.model.decoder.layers.34.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 590 |
+
"decoder.model.decoder.layers.34.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 591 |
+
"decoder.model.decoder.layers.34.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 592 |
+
"decoder.model.decoder.layers.34.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 593 |
+
"decoder.model.decoder.layers.34.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 594 |
+
"decoder.model.decoder.layers.34.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 595 |
+
"decoder.model.decoder.layers.34.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 596 |
+
"decoder.model.decoder.layers.34.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 597 |
+
"decoder.model.decoder.layers.35.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 598 |
+
"decoder.model.decoder.layers.35.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 599 |
+
"decoder.model.decoder.layers.35.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 600 |
+
"decoder.model.decoder.layers.35.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 601 |
+
"decoder.model.decoder.layers.35.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 602 |
+
"decoder.model.decoder.layers.35.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 603 |
+
"decoder.model.decoder.layers.35.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 604 |
+
"decoder.model.decoder.layers.35.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 605 |
+
"decoder.model.decoder.layers.35.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 606 |
+
"decoder.model.decoder.layers.35.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 607 |
+
"decoder.model.decoder.layers.35.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 608 |
+
"decoder.model.decoder.layers.35.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 609 |
+
"decoder.model.decoder.layers.35.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 610 |
+
"decoder.model.decoder.layers.35.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 611 |
+
"decoder.model.decoder.layers.35.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 612 |
+
"decoder.model.decoder.layers.35.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 613 |
+
"decoder.model.decoder.layers.36.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 614 |
+
"decoder.model.decoder.layers.36.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 615 |
+
"decoder.model.decoder.layers.36.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 616 |
+
"decoder.model.decoder.layers.36.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 617 |
+
"decoder.model.decoder.layers.36.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 618 |
+
"decoder.model.decoder.layers.36.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 619 |
+
"decoder.model.decoder.layers.36.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 620 |
+
"decoder.model.decoder.layers.36.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 621 |
+
"decoder.model.decoder.layers.36.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 622 |
+
"decoder.model.decoder.layers.36.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 623 |
+
"decoder.model.decoder.layers.36.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 624 |
+
"decoder.model.decoder.layers.36.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 625 |
+
"decoder.model.decoder.layers.36.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 626 |
+
"decoder.model.decoder.layers.36.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 627 |
+
"decoder.model.decoder.layers.36.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 628 |
+
"decoder.model.decoder.layers.36.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 629 |
+
"decoder.model.decoder.layers.37.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 630 |
+
"decoder.model.decoder.layers.37.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 631 |
+
"decoder.model.decoder.layers.37.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 632 |
+
"decoder.model.decoder.layers.37.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 633 |
+
"decoder.model.decoder.layers.37.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 634 |
+
"decoder.model.decoder.layers.37.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 635 |
+
"decoder.model.decoder.layers.37.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 636 |
+
"decoder.model.decoder.layers.37.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 637 |
+
"decoder.model.decoder.layers.37.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 638 |
+
"decoder.model.decoder.layers.37.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 639 |
+
"decoder.model.decoder.layers.37.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 640 |
+
"decoder.model.decoder.layers.37.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 641 |
+
"decoder.model.decoder.layers.37.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 642 |
+
"decoder.model.decoder.layers.37.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 643 |
+
"decoder.model.decoder.layers.37.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 644 |
+
"decoder.model.decoder.layers.37.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 645 |
+
"decoder.model.decoder.layers.38.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 646 |
+
"decoder.model.decoder.layers.38.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 647 |
+
"decoder.model.decoder.layers.38.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 648 |
+
"decoder.model.decoder.layers.38.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 649 |
+
"decoder.model.decoder.layers.38.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 650 |
+
"decoder.model.decoder.layers.38.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 651 |
+
"decoder.model.decoder.layers.38.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 652 |
+
"decoder.model.decoder.layers.38.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 653 |
+
"decoder.model.decoder.layers.38.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 654 |
+
"decoder.model.decoder.layers.38.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 655 |
+
"decoder.model.decoder.layers.38.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 656 |
+
"decoder.model.decoder.layers.38.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 657 |
+
"decoder.model.decoder.layers.38.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 658 |
+
"decoder.model.decoder.layers.38.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 659 |
+
"decoder.model.decoder.layers.38.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 660 |
+
"decoder.model.decoder.layers.38.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 661 |
+
"decoder.model.decoder.layers.39.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 662 |
+
"decoder.model.decoder.layers.39.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 663 |
+
"decoder.model.decoder.layers.39.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 664 |
+
"decoder.model.decoder.layers.39.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 665 |
+
"decoder.model.decoder.layers.39.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 666 |
+
"decoder.model.decoder.layers.39.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 667 |
+
"decoder.model.decoder.layers.39.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 668 |
+
"decoder.model.decoder.layers.39.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 669 |
+
"decoder.model.decoder.layers.39.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 670 |
+
"decoder.model.decoder.layers.39.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 671 |
+
"decoder.model.decoder.layers.39.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 672 |
+
"decoder.model.decoder.layers.39.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 673 |
+
"decoder.model.decoder.layers.39.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 674 |
+
"decoder.model.decoder.layers.39.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 675 |
+
"decoder.model.decoder.layers.39.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 676 |
+
"decoder.model.decoder.layers.39.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 677 |
+
"decoder.model.decoder.layers.4.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 678 |
+
"decoder.model.decoder.layers.4.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 679 |
+
"decoder.model.decoder.layers.4.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 680 |
+
"decoder.model.decoder.layers.4.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 681 |
+
"decoder.model.decoder.layers.4.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 682 |
+
"decoder.model.decoder.layers.4.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 683 |
+
"decoder.model.decoder.layers.4.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 684 |
+
"decoder.model.decoder.layers.4.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 685 |
+
"decoder.model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 686 |
+
"decoder.model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 687 |
+
"decoder.model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 688 |
+
"decoder.model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 689 |
+
"decoder.model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 690 |
+
"decoder.model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 691 |
+
"decoder.model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 692 |
+
"decoder.model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 693 |
+
"decoder.model.decoder.layers.40.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 694 |
+
"decoder.model.decoder.layers.40.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 695 |
+
"decoder.model.decoder.layers.40.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 696 |
+
"decoder.model.decoder.layers.40.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 697 |
+
"decoder.model.decoder.layers.40.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 698 |
+
"decoder.model.decoder.layers.40.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 699 |
+
"decoder.model.decoder.layers.40.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 700 |
+
"decoder.model.decoder.layers.40.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 701 |
+
"decoder.model.decoder.layers.40.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 702 |
+
"decoder.model.decoder.layers.40.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 703 |
+
"decoder.model.decoder.layers.40.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 704 |
+
"decoder.model.decoder.layers.40.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 705 |
+
"decoder.model.decoder.layers.40.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 706 |
+
"decoder.model.decoder.layers.40.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 707 |
+
"decoder.model.decoder.layers.40.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 708 |
+
"decoder.model.decoder.layers.40.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 709 |
+
"decoder.model.decoder.layers.41.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 710 |
+
"decoder.model.decoder.layers.41.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 711 |
+
"decoder.model.decoder.layers.41.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 712 |
+
"decoder.model.decoder.layers.41.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 713 |
+
"decoder.model.decoder.layers.41.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 714 |
+
"decoder.model.decoder.layers.41.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 715 |
+
"decoder.model.decoder.layers.41.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 716 |
+
"decoder.model.decoder.layers.41.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 717 |
+
"decoder.model.decoder.layers.41.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 718 |
+
"decoder.model.decoder.layers.41.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 719 |
+
"decoder.model.decoder.layers.41.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 720 |
+
"decoder.model.decoder.layers.41.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 721 |
+
"decoder.model.decoder.layers.41.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 722 |
+
"decoder.model.decoder.layers.41.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 723 |
+
"decoder.model.decoder.layers.41.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 724 |
+
"decoder.model.decoder.layers.41.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 725 |
+
"decoder.model.decoder.layers.42.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 726 |
+
"decoder.model.decoder.layers.42.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 727 |
+
"decoder.model.decoder.layers.42.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 728 |
+
"decoder.model.decoder.layers.42.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 729 |
+
"decoder.model.decoder.layers.42.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 730 |
+
"decoder.model.decoder.layers.42.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 731 |
+
"decoder.model.decoder.layers.42.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 732 |
+
"decoder.model.decoder.layers.42.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 733 |
+
"decoder.model.decoder.layers.42.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 734 |
+
"decoder.model.decoder.layers.42.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 735 |
+
"decoder.model.decoder.layers.42.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 736 |
+
"decoder.model.decoder.layers.42.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 737 |
+
"decoder.model.decoder.layers.42.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 738 |
+
"decoder.model.decoder.layers.42.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 739 |
+
"decoder.model.decoder.layers.42.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 740 |
+
"decoder.model.decoder.layers.42.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 741 |
+
"decoder.model.decoder.layers.43.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 742 |
+
"decoder.model.decoder.layers.43.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 743 |
+
"decoder.model.decoder.layers.43.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 744 |
+
"decoder.model.decoder.layers.43.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 745 |
+
"decoder.model.decoder.layers.43.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 746 |
+
"decoder.model.decoder.layers.43.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 747 |
+
"decoder.model.decoder.layers.43.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 748 |
+
"decoder.model.decoder.layers.43.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 749 |
+
"decoder.model.decoder.layers.43.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 750 |
+
"decoder.model.decoder.layers.43.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 751 |
+
"decoder.model.decoder.layers.43.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 752 |
+
"decoder.model.decoder.layers.43.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 753 |
+
"decoder.model.decoder.layers.43.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 754 |
+
"decoder.model.decoder.layers.43.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 755 |
+
"decoder.model.decoder.layers.43.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 756 |
+
"decoder.model.decoder.layers.43.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 757 |
+
"decoder.model.decoder.layers.44.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 758 |
+
"decoder.model.decoder.layers.44.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 759 |
+
"decoder.model.decoder.layers.44.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 760 |
+
"decoder.model.decoder.layers.44.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 761 |
+
"decoder.model.decoder.layers.44.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 762 |
+
"decoder.model.decoder.layers.44.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 763 |
+
"decoder.model.decoder.layers.44.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 764 |
+
"decoder.model.decoder.layers.44.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 765 |
+
"decoder.model.decoder.layers.44.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 766 |
+
"decoder.model.decoder.layers.44.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 767 |
+
"decoder.model.decoder.layers.44.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 768 |
+
"decoder.model.decoder.layers.44.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 769 |
+
"decoder.model.decoder.layers.44.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 770 |
+
"decoder.model.decoder.layers.44.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 771 |
+
"decoder.model.decoder.layers.44.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 772 |
+
"decoder.model.decoder.layers.44.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 773 |
+
"decoder.model.decoder.layers.45.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 774 |
+
"decoder.model.decoder.layers.45.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 775 |
+
"decoder.model.decoder.layers.45.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 776 |
+
"decoder.model.decoder.layers.45.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 777 |
+
"decoder.model.decoder.layers.45.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 778 |
+
"decoder.model.decoder.layers.45.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 779 |
+
"decoder.model.decoder.layers.45.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 780 |
+
"decoder.model.decoder.layers.45.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 781 |
+
"decoder.model.decoder.layers.45.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 782 |
+
"decoder.model.decoder.layers.45.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 783 |
+
"decoder.model.decoder.layers.45.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 784 |
+
"decoder.model.decoder.layers.45.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 785 |
+
"decoder.model.decoder.layers.45.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 786 |
+
"decoder.model.decoder.layers.45.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 787 |
+
"decoder.model.decoder.layers.45.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 788 |
+
"decoder.model.decoder.layers.45.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 789 |
+
"decoder.model.decoder.layers.46.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 790 |
+
"decoder.model.decoder.layers.46.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 791 |
+
"decoder.model.decoder.layers.46.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 792 |
+
"decoder.model.decoder.layers.46.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 793 |
+
"decoder.model.decoder.layers.46.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 794 |
+
"decoder.model.decoder.layers.46.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 795 |
+
"decoder.model.decoder.layers.46.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 796 |
+
"decoder.model.decoder.layers.46.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 797 |
+
"decoder.model.decoder.layers.46.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 798 |
+
"decoder.model.decoder.layers.46.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 799 |
+
"decoder.model.decoder.layers.46.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 800 |
+
"decoder.model.decoder.layers.46.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 801 |
+
"decoder.model.decoder.layers.46.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 802 |
+
"decoder.model.decoder.layers.46.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 803 |
+
"decoder.model.decoder.layers.46.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 804 |
+
"decoder.model.decoder.layers.46.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 805 |
+
"decoder.model.decoder.layers.47.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 806 |
+
"decoder.model.decoder.layers.47.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 807 |
+
"decoder.model.decoder.layers.47.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 808 |
+
"decoder.model.decoder.layers.47.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 809 |
+
"decoder.model.decoder.layers.47.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 810 |
+
"decoder.model.decoder.layers.47.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 811 |
+
"decoder.model.decoder.layers.47.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
| 812 |
+
"decoder.model.decoder.layers.47.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
| 813 |
+
"decoder.model.decoder.layers.47.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 814 |
+
"decoder.model.decoder.layers.47.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 815 |
+
"decoder.model.decoder.layers.47.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 816 |
+
"decoder.model.decoder.layers.47.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 817 |
+
"decoder.model.decoder.layers.47.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 818 |
+
"decoder.model.decoder.layers.47.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 819 |
+
"decoder.model.decoder.layers.47.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
| 820 |
+
"decoder.model.decoder.layers.47.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 821 |
+
"decoder.model.decoder.layers.5.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 822 |
+
"decoder.model.decoder.layers.5.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 823 |
+
"decoder.model.decoder.layers.5.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 824 |
+
"decoder.model.decoder.layers.5.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 825 |
+
"decoder.model.decoder.layers.5.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 826 |
+
"decoder.model.decoder.layers.5.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 827 |
+
"decoder.model.decoder.layers.5.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 828 |
+
"decoder.model.decoder.layers.5.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 829 |
+
"decoder.model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 830 |
+
"decoder.model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 831 |
+
"decoder.model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 832 |
+
"decoder.model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 833 |
+
"decoder.model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 834 |
+
"decoder.model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 835 |
+
"decoder.model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 836 |
+
"decoder.model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 837 |
+
"decoder.model.decoder.layers.6.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 838 |
+
"decoder.model.decoder.layers.6.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 839 |
+
"decoder.model.decoder.layers.6.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 840 |
+
"decoder.model.decoder.layers.6.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 841 |
+
"decoder.model.decoder.layers.6.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 842 |
+
"decoder.model.decoder.layers.6.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 843 |
+
"decoder.model.decoder.layers.6.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 844 |
+
"decoder.model.decoder.layers.6.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 845 |
+
"decoder.model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 846 |
+
"decoder.model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 847 |
+
"decoder.model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 848 |
+
"decoder.model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 849 |
+
"decoder.model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 850 |
+
"decoder.model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 851 |
+
"decoder.model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 852 |
+
"decoder.model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 853 |
+
"decoder.model.decoder.layers.7.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 854 |
+
"decoder.model.decoder.layers.7.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 855 |
+
"decoder.model.decoder.layers.7.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 856 |
+
"decoder.model.decoder.layers.7.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 857 |
+
"decoder.model.decoder.layers.7.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 858 |
+
"decoder.model.decoder.layers.7.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 859 |
+
"decoder.model.decoder.layers.7.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 860 |
+
"decoder.model.decoder.layers.7.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 861 |
+
"decoder.model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 862 |
+
"decoder.model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 863 |
+
"decoder.model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 864 |
+
"decoder.model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 865 |
+
"decoder.model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 866 |
+
"decoder.model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 867 |
+
"decoder.model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 868 |
+
"decoder.model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 869 |
+
"decoder.model.decoder.layers.8.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 870 |
+
"decoder.model.decoder.layers.8.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 871 |
+
"decoder.model.decoder.layers.8.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 872 |
+
"decoder.model.decoder.layers.8.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 873 |
+
"decoder.model.decoder.layers.8.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 874 |
+
"decoder.model.decoder.layers.8.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 875 |
+
"decoder.model.decoder.layers.8.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 876 |
+
"decoder.model.decoder.layers.8.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 877 |
+
"decoder.model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 878 |
+
"decoder.model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 879 |
+
"decoder.model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 880 |
+
"decoder.model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 881 |
+
"decoder.model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 882 |
+
"decoder.model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 883 |
+
"decoder.model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 884 |
+
"decoder.model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 885 |
+
"decoder.model.decoder.layers.9.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 886 |
+
"decoder.model.decoder.layers.9.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 887 |
+
"decoder.model.decoder.layers.9.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 888 |
+
"decoder.model.decoder.layers.9.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 889 |
+
"decoder.model.decoder.layers.9.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 890 |
+
"decoder.model.decoder.layers.9.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 891 |
+
"decoder.model.decoder.layers.9.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
| 892 |
+
"decoder.model.decoder.layers.9.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
| 893 |
+
"decoder.model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 894 |
+
"decoder.model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 895 |
+
"decoder.model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 896 |
+
"decoder.model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 897 |
+
"decoder.model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 898 |
+
"decoder.model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 899 |
+
"decoder.model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
| 900 |
+
"decoder.model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 901 |
+
"enc_to_dec_proj.bias": "pytorch_model-00002-of-00002.bin",
|
| 902 |
+
"enc_to_dec_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 903 |
+
"text_encoder.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 904 |
+
"text_encoder.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 905 |
+
"text_encoder.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 906 |
+
"text_encoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
|
| 907 |
+
"text_encoder.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 908 |
+
"text_encoder.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 909 |
+
"text_encoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 910 |
+
"text_encoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 911 |
+
"text_encoder.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 912 |
+
"text_encoder.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 913 |
+
"text_encoder.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 914 |
+
"text_encoder.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 915 |
+
"text_encoder.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 916 |
+
"text_encoder.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 917 |
+
"text_encoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 918 |
+
"text_encoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 919 |
+
"text_encoder.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 920 |
+
"text_encoder.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 921 |
+
"text_encoder.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 922 |
+
"text_encoder.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 923 |
+
"text_encoder.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 924 |
+
"text_encoder.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 925 |
+
"text_encoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 926 |
+
"text_encoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 927 |
+
"text_encoder.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 928 |
+
"text_encoder.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 929 |
+
"text_encoder.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 930 |
+
"text_encoder.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 931 |
+
"text_encoder.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 932 |
+
"text_encoder.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 933 |
+
"text_encoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 934 |
+
"text_encoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 935 |
+
"text_encoder.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 936 |
+
"text_encoder.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 937 |
+
"text_encoder.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 938 |
+
"text_encoder.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 939 |
+
"text_encoder.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 940 |
+
"text_encoder.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 941 |
+
"text_encoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 942 |
+
"text_encoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 943 |
+
"text_encoder.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 944 |
+
"text_encoder.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 945 |
+
"text_encoder.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 946 |
+
"text_encoder.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 947 |
+
"text_encoder.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 948 |
+
"text_encoder.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 949 |
+
"text_encoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 950 |
+
"text_encoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 951 |
+
"text_encoder.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 952 |
+
"text_encoder.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 953 |
+
"text_encoder.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 954 |
+
"text_encoder.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 955 |
+
"text_encoder.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 956 |
+
"text_encoder.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 957 |
+
"text_encoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 958 |
+
"text_encoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 959 |
+
"text_encoder.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 960 |
+
"text_encoder.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 961 |
+
"text_encoder.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 962 |
+
"text_encoder.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 963 |
+
"text_encoder.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 964 |
+
"text_encoder.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 965 |
+
"text_encoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 966 |
+
"text_encoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 967 |
+
"text_encoder.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 968 |
+
"text_encoder.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 969 |
+
"text_encoder.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 970 |
+
"text_encoder.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 971 |
+
"text_encoder.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 972 |
+
"text_encoder.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 973 |
+
"text_encoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 974 |
+
"text_encoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 975 |
+
"text_encoder.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 976 |
+
"text_encoder.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 977 |
+
"text_encoder.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 978 |
+
"text_encoder.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 979 |
+
"text_encoder.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 980 |
+
"text_encoder.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 981 |
+
"text_encoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 982 |
+
"text_encoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 983 |
+
"text_encoder.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 984 |
+
"text_encoder.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 985 |
+
"text_encoder.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 986 |
+
"text_encoder.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 987 |
+
"text_encoder.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 988 |
+
"text_encoder.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 989 |
+
"text_encoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 990 |
+
"text_encoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 991 |
+
"text_encoder.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 992 |
+
"text_encoder.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 993 |
+
"text_encoder.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 994 |
+
"text_encoder.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 995 |
+
"text_encoder.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 996 |
+
"text_encoder.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 997 |
+
"text_encoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
|
| 998 |
+
"text_encoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 999 |
+
"text_encoder.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 1000 |
+
"text_encoder.encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
| 1001 |
+
"text_encoder.encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 1002 |
+
"text_encoder.shared.weight": "pytorch_model-00001-of-00002.bin"
|
| 1003 |
+
}
|
| 1004 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
state_dict.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f0cf17b5e65c5dd8ba71767371c377f174e4ce1db44bc4d6657825769f26ffd
|
| 3 |
+
size 6514108999
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"clean_up_tokenization_spaces": true,
|
| 105 |
+
"eos_token": "</s>",
|
| 106 |
+
"extra_ids": 100,
|
| 107 |
+
"model_max_length": 512,
|
| 108 |
+
"pad_token": "<pad>",
|
| 109 |
+
"processor_class": "MusicgenProcessor",
|
| 110 |
+
"tokenizer_class": "T5Tokenizer",
|
| 111 |
+
"unk_token": "<unk>"
|
| 112 |
+
}
|