Commit ·
3fbe385
0
Parent(s):
Duplicate from XiaomiMiMo/MiMo-V2.5-ASR
Browse filesCo-authored-by: chen <MarkDaniel212@users.noreply.huggingface.co>
- .gitattributes +39 -0
- README.md +195 -0
- added_tokens.json +32 -0
- assets/MiMo_ASR_Demo.png +3 -0
- assets/MiMo_ASR_Results.png +3 -0
- assets/XiaomiMIMO.png +3 -0
- chat_template.jinja +170 -0
- config.json +108 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +727 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +271 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
assets/MiMo_ASR_Demo.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
assets/XiaomiMIMO.png filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
assets/MiMo_ASR_Results.png filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
language:
|
| 5 |
+
- zh
|
| 6 |
+
- en
|
| 7 |
+
- yue
|
| 8 |
+
pipeline_tag: automatic-speech-recognition
|
| 9 |
+
tags:
|
| 10 |
+
- safetensors
|
| 11 |
+
- text-generation-inference
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<div align="center">
|
| 15 |
+
<picture>
|
| 16 |
+
<source srcset="https://huggingface.co/XiaomiMiMo/MiMo-V2.5-ASR/resolve/main/assets/XiaomiMIMO.png" media="(prefers-color-scheme: dark)">
|
| 17 |
+
<img src="https://huggingface.co/XiaomiMiMo/MiMo-V2.5-ASR/resolve/main/assets/XiaomiMIMO.png" width="60%" alt="Xiaomi-MiMo" />
|
| 18 |
+
</picture>
|
| 19 |
+
</div>
|
| 20 |
+
|
| 21 |
+
<div align="center">
|
| 22 |
+
<h3>
|
| 23 |
+
<b>
|
| 24 |
+
<span>━━━━━━━━━━━━━━━━━━━━━━━━━━━</span><br/>
|
| 25 |
+
MiMo-V2.5-ASR: Robust Speech Recognition Across<br/>
|
| 26 |
+
Languages, Dialects, and Complex Acoustic Scenarios<br/>
|
| 27 |
+
<span>━━━━━━━━━━━━━━━━━━━━━━━━━━━</span>
|
| 28 |
+
</b>
|
| 29 |
+
</h3>
|
| 30 |
+
</div>
|
| 31 |
+
|
| 32 |
+
<br/>
|
| 33 |
+
|
| 34 |
+
<div align="center" style="line-height: 1;">
|
| 35 |
+
|
|
| 36 |
+
<a href="https://github.com/XiaomiMiMo/MiMo-V2.5-ASR" target="_blank">💻 GitHub</a>
|
| 37 |
+
|
|
| 38 |
+
<a href="https://huggingface.co/spaces/XiaomiMiMo/MiMo-V2.5-ASR" target="_blank">🚀 Online Demo</a>
|
| 39 |
+
|
|
| 40 |
+
<a href="https://mimo.xiaomi.com/mimo-v2-5-asr" target="_blank">📰 Blog</a>
|
| 41 |
+
|
|
| 42 |
+
|
| 43 |
+
<br/>
|
| 44 |
+
</div>
|
| 45 |
+
|
| 46 |
+
<br/>
|
| 47 |
+
|
| 48 |
+
## Introduction
|
| 49 |
+
|
| 50 |
+
**MiMo-V2.5-ASR** is a state-of-the-art end-to-end automatic speech recognition (ASR) model developed by the Xiaomi MiMo team. It is built to deliver accurate and robust transcription across Mandarin Chinese and English, multiple Chinese dialects, code-switched speech, song lyrics, knowledge-intensive content, noisy acoustic environments, and multi-speaker conversations. MiMo-V2.5-ASR achieves state-of-the-art results on a wide range of public benchmarks.
|
| 51 |
+
|
| 52 |
+
## Abstract
|
| 53 |
+
|
| 54 |
+
Automatic speech recognition systems are expected to faithfully transcribe speech signals that originate from diverse languages, dialects, accents, and domains, and that are captured under a wide variety of acoustic conditions. While conventional end-to-end models perform well on in-domain data, they still fall short of real-world requirements in challenging scenarios such as dialect mixing, code-switching, knowledge-intensive content, noisy environments, and multi-speaker conversations. We present **MiMo-V2.5-ASR**, a large-scale end-to-end speech recognition model developed by the Xiaomi MiMo team. Through large-scale mid-training, high-quality supervised fine-tuning, and a novel reinforcement-learning algorithm, MiMo-V2.5-ASR achieves systematic improvements along the following dimensions:
|
| 55 |
+
|
| 56 |
+
- 🗣️ **Chinese Dialects**: Native support for Wu, Cantonese, Hokkien, Sichuanese, and more.
|
| 57 |
+
- 🔀 **Code-Switch**: Seamless Chinese–English code-switching transcription with no language tags required.
|
| 58 |
+
- 🎵 **Song Recognition**: High-precision lyrics transcription for Chinese and English songs, even with mixed accompaniment and vocals.
|
| 59 |
+
- 🔊 **Noisy Environments**: Robust recognition under heavy noise, far-field capture, and other adverse acoustic conditions.
|
| 60 |
+
- 👥 **Multi-Speaker**: Accurate transcription of overlapping, multi-party conversations such as meetings.
|
| 61 |
+
- 🇬🇧 **Complex English Scenarios**: Leading performance on the [Open ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard) for challenging English benchmarks such as AMI.
|
| 62 |
+
- 📚 **Knowledge-Intensive Recognition**: Precise recognition of classical poetry, technical terminology, personal names, place names, and other knowledge-dense material.
|
| 63 |
+
- 📝 **Native Punctuation**: Punctuation generated natively from prosody and semantics, delivering ready-to-use transcripts with no post-processing needed.
|
| 64 |
+
|
| 65 |
+
## Results
|
| 66 |
+
|
| 67 |
+
MiMo-V2.5-ASR has been evaluated across a broad set of benchmarks spanning standard Mandarin and English, Chinese dialects, lyric recognition, and internal business scenarios. The chart below summarizes the average performance of MiMo-V2.5-ASR across these scenarios.
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
For per-benchmark numbers and specific qualitative cases, please refer to our [blog](https://mimo.xiaomi.com/mimo-v2-5-asr).
|
| 72 |
+
|
| 73 |
+
## Model Download
|
| 74 |
+
|
| 75 |
+
| Models | 🤗 Hugging Face | 🤖️ ModelScope |
|
| 76 |
+
|-------|-------|-------|
|
| 77 |
+
| MiMo-Audio-Tokenizer | [XiaomiMiMo/MiMo-Audio-Tokenizer](https://huggingface.co/XiaomiMiMo/MiMo-Audio-Tokenizer) | [XiaomiMiMo/MiMo-Audio-Tokenizer](https://modelscope.cn/models/XiaomiMiMo/MiMo-Audio-Tokenizer)|
|
| 78 |
+
| MiMo-V2.5-ASR | [XiaomiMiMo/MiMo-V2.5-ASR](https://huggingface.co/XiaomiMiMo/MiMo-V2.5-ASR) | [XiaomiMiMo/MiMo-V2.5-ASR](https://modelscope.cn/models/XiaomiMiMo/MiMo-V2.5-ASR) |
|
| 79 |
+
|
| 80 |
+
```bash
|
| 81 |
+
pip install huggingface-hub
|
| 82 |
+
|
| 83 |
+
hf download XiaomiMiMo/MiMo-Audio-Tokenizer --local-dir ./models/MiMo-Audio-Tokenizer
|
| 84 |
+
hf download XiaomiMiMo/MiMo-V2.5-ASR --local-dir ./models/MiMo-V2.5-ASR
|
| 85 |
+
```
|
| 86 |
+
|
| 87 |
+
## Getting Started
|
| 88 |
+
|
| 89 |
+
Spin up the MiMo-V2.5-ASR demo in minutes with the built-in Gradio app.
|
| 90 |
+
|
| 91 |
+
### Prerequisites (Linux)
|
| 92 |
+
|
| 93 |
+
* Python 3.12
|
| 94 |
+
* CUDA >= 12.0
|
| 95 |
+
|
| 96 |
+
### Installation
|
| 97 |
+
|
| 98 |
+
```bash
|
| 99 |
+
git clone https://github.com/XiaomiMiMo/MiMo-V2.5-ASR.git
|
| 100 |
+
cd MiMo-V2.5-ASR
|
| 101 |
+
pip install -r requirements.txt
|
| 102 |
+
pip install flash-attn==2.7.4.post1
|
| 103 |
+
```
|
| 104 |
+
|
| 105 |
+
> \[!Note]
|
| 106 |
+
> If the compilation of flash-attn takes too long, you can download the precompiled wheel and install it manually:
|
| 107 |
+
>
|
| 108 |
+
> * [Download Precompiled Wheel](https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp312-cp312-linux_x86_64.whl)
|
| 109 |
+
>
|
| 110 |
+
> ```sh
|
| 111 |
+
> pip install /path/to/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp312-cp312-linux_x86_64.whl
|
| 112 |
+
> ```
|
| 113 |
+
|
| 114 |
+
### Run the Demo
|
| 115 |
+
|
| 116 |
+
```bash
|
| 117 |
+
python run_mimo_asr.py
|
| 118 |
+
```
|
| 119 |
+
|
| 120 |
+
This launches a local Gradio interface for MiMo-V2.5-ASR. You can:
|
| 121 |
+
|
| 122 |
+
* Upload an audio file **or** record directly from your microphone.
|
| 123 |
+
* Optionally specify a **language tag** (Chinese / English / Auto) to bias the model for a specific language, or leave it to **Auto** for automatic language detection (recommended for code-switched speech).
|
| 124 |
+
* The demo calls the `asr_sft()` interface under the hood.
|
| 125 |
+
|
| 126 |
+
The interface provides a **Model Configuration** tab for setting local model and tokenizer paths, and a **Speech Recognition** tab where you drop in audio, pick a language tag, and hit *Transcribe* — the decoded text and processing status stream into the panels on the right.
|
| 127 |
+
|
| 128 |
+
<p align="center">
|
| 129 |
+
<img src="https://huggingface.co/XiaomiMiMo/MiMo-V2.5-ASR/resolve/main/assets/MiMo_ASR_Demo.png" alt="MiMo-V2.5-ASR Gradio Demo" width="90%" />
|
| 130 |
+
<br/>
|
| 131 |
+
<em>Figure: Gradio demo for MiMo-V2.5-ASR — upload an audio clip or record from your microphone, choose a language tag, and get the transcription on the right.</em>
|
| 132 |
+
</p>
|
| 133 |
+
|
| 134 |
+
To load the model and tokenizer automatically at startup, pass their paths on the command line:
|
| 135 |
+
|
| 136 |
+
```bash
|
| 137 |
+
python run_mimo_asr.py \
|
| 138 |
+
--model-path ./models/MiMo-V2.5-ASR \
|
| 139 |
+
--tokenizer-path ./models/MiMo-Audio-Tokenizer
|
| 140 |
+
```
|
| 141 |
+
|
| 142 |
+
Otherwise, enter the local paths for `MiMo-Audio-Tokenizer` and `MiMo-V2.5-ASR` in the **Model Configuration** tab, then start transcribing!
|
| 143 |
+
|
| 144 |
+
## Python API
|
| 145 |
+
|
| 146 |
+
Basic usage with the `asr_sft` interface:
|
| 147 |
+
|
| 148 |
+
```python
|
| 149 |
+
from src.mimo_audio.mimo_audio import MimoAudio
|
| 150 |
+
|
| 151 |
+
model = MimoAudio(
|
| 152 |
+
model_path="./models/MiMo-V2.5-ASR",
|
| 153 |
+
tokenizer_path="./models/MiMo-Audio-Tokenizer",
|
| 154 |
+
)
|
| 155 |
+
|
| 156 |
+
# Automatic language detection (recommended for code-switching)
|
| 157 |
+
text = model.asr_sft("path/to/audio.wav")
|
| 158 |
+
print(text)
|
| 159 |
+
|
| 160 |
+
# With explicit language tag
|
| 161 |
+
text_zh = model.asr_sft("path/to/audio.wav", audio_tag="<chinese>")
|
| 162 |
+
text_en = model.asr_sft("path/to/audio.wav", audio_tag="<english>")
|
| 163 |
+
```
|
| 164 |
+
|
| 165 |
+
## Citation
|
| 166 |
+
|
| 167 |
+
```bibtex
|
| 168 |
+
@misc{coreteam2026mimov25asr,
|
| 169 |
+
title={MiMo-V2.5-ASR: Robust Speech Recognition Across Languages, Dialects, and Complex Acoustic Scenarios},
|
| 170 |
+
author={LLM-Core-Team Xiaomi},
|
| 171 |
+
year={2026},
|
| 172 |
+
url={https://github.com/XiaomiMiMo/MiMo-V2.5-ASR},
|
| 173 |
+
}
|
| 174 |
+
```
|
| 175 |
+
|
| 176 |
+
## Contact
|
| 177 |
+
|
| 178 |
+
Please contact us at [mimo@xiaomi.com](mailto:mimo@xiaomi.com) or open an issue if you have any questions.
|
| 179 |
+
|
| 180 |
+
## Use Restrictions
|
| 181 |
+
|
| 182 |
+
You are solely responsible for your use of XiaomiMiMo/MiMo-V2.5-ASR and any outputs, actions, or consequences arising therefrom, and you agree not to use the XiaomiMiMo/MiMo-V2.5-ASR or any derivatives thereof:
|
| 183 |
+
- For any unlawful, fraudulent, or malicious purpose, or in any manner that violates any applicable laws or regulations；
|
| 184 |
+
- To infringe upon the intellectual property rights, privacy rights, publicity rights, or other lawful rights or interests of any third party;
|
| 185 |
+
- To exploit, harm, harass, defame, unlawfully discriminate against, or otherwise adversely affect any individual or group, including minors or vulnerable persons;
|
| 186 |
+
- For any military purpose or application;
|
| 187 |
+
- To engage in or facilitate malicious cyber activities, including but not limited to malware, ransomware, phishing, credential theft, or unauthorized access, or any activity intended to compromise or unlawfully control computer systems, networks, or encryption systems;
|
| 188 |
+
- To access, collect, process, disclose, or disseminate personal data or other protected information without appropriate authorization or lawful basis; or to access, interact with, scrape, or automate any third-party platform or service in violation of any applicable laws, policies, or authorization requirements;
|
| 189 |
+
- To use the XiaomiMiMo/MiMo-V2.5-ASR in a manner that autonomously executes high-risk actions without appropriate human oversight or authorization.
|
| 190 |
+
|
| 191 |
+
This notice is an informational reminder only and does not amend the applicable model licence or impose additional licence conditions. The permissions granted under that licence remain unaffected. Nothing in this notice restricts uses permitted by applicable law, including applicable exceptions and limitations.
|
| 192 |
+
|
| 193 |
+
### Usage enquiries and complaints
|
| 194 |
+
|
| 195 |
+
[mimo-legal@xiaomi.com](mailto:mimo-legal@xiaomi.com). For information on submitting a complaint, please visit the https://mimo.xiaomi.com.
|
added_tokens.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|Human|>": 151668,
|
| 5 |
+
"<|SpeechLM|>": 151669,
|
| 6 |
+
"<|box_end|>": 151649,
|
| 7 |
+
"<|box_start|>": 151648,
|
| 8 |
+
"<|empty|>": 151667,
|
| 9 |
+
"<|endoftext|>": 151643,
|
| 10 |
+
"<|eosp|>": 151666,
|
| 11 |
+
"<|eostm|>": 151671,
|
| 12 |
+
"<|eot|>": 151672,
|
| 13 |
+
"<|file_sep|>": 151664,
|
| 14 |
+
"<|fim_middle|>": 151660,
|
| 15 |
+
"<|fim_pad|>": 151662,
|
| 16 |
+
"<|fim_prefix|>": 151659,
|
| 17 |
+
"<|fim_suffix|>": 151661,
|
| 18 |
+
"<|im_end|>": 151645,
|
| 19 |
+
"<|im_start|>": 151644,
|
| 20 |
+
"<|image_pad|>": 151655,
|
| 21 |
+
"<|object_ref_end|>": 151647,
|
| 22 |
+
"<|object_ref_start|>": 151646,
|
| 23 |
+
"<|quad_end|>": 151651,
|
| 24 |
+
"<|quad_start|>": 151650,
|
| 25 |
+
"<|repo_name|>": 151663,
|
| 26 |
+
"<|sosp|>": 151665,
|
| 27 |
+
"<|sostm|>": 151670,
|
| 28 |
+
"<|video_pad|>": 151656,
|
| 29 |
+
"<|vision_end|>": 151653,
|
| 30 |
+
"<|vision_pad|>": 151654,
|
| 31 |
+
"<|vision_start|>": 151652
|
| 32 |
+
}
|
assets/MiMo_ASR_Demo.png
ADDED
|
Git LFS Details
|
assets/MiMo_ASR_Results.png
ADDED
|
Git LFS Details
|
assets/XiaomiMIMO.png
ADDED
|
Git LFS Details
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if not add_generation_prompt is defined -%}
|
| 2 |
+
{%- set add_generation_prompt = false -%}
|
| 3 |
+
{%- endif -%}
|
| 4 |
+
{%- if not enable_thinking is defined -%}
|
| 5 |
+
{%- set enable_thinking = false -%}
|
| 6 |
+
{%- endif -%}
|
| 7 |
+
{%- if not keep_all_reasoning is defined -%}
|
| 8 |
+
{%- set keep_all_reasoning = false -%}
|
| 9 |
+
{%- endif -%}
|
| 10 |
+
{%- macro render_extra_keys(json_dict, handled_keys) -%}
|
| 11 |
+
{%- if json_dict is mapping %}
|
| 12 |
+
{%- for json_key in json_dict if json_key not in handled_keys %}
|
| 13 |
+
{%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
|
| 14 |
+
{{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
|
| 15 |
+
{%- else %}
|
| 16 |
+
{{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{%- endfor %}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endmacro -%}
|
| 21 |
+
{%- macro render_content(message_content) -%}
|
| 22 |
+
{%- if message_content is string -%}
|
| 23 |
+
{{- message_content -}}
|
| 24 |
+
{%- else -%}
|
| 25 |
+
{%- for content in message_content -%}
|
| 26 |
+
{%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}
|
| 27 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' -}}
|
| 28 |
+
{%- elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content -%}
|
| 29 |
+
{{- '<|sosp|><|empty|><|eosp|>' -}}
|
| 30 |
+
{%- elif content['type'] == 'video' or 'video' in content or 'video_url' in content -%}
|
| 31 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' -}}
|
| 32 |
+
{%- elif 'text' in content -%}
|
| 33 |
+
{{- content['text'] -}}
|
| 34 |
+
{%- endif -%}
|
| 35 |
+
{%- endfor -%}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endmacro -%}
|
| 38 |
+
{%- if messages[0]["role"] == "system" %}
|
| 39 |
+
{%- set system_message = messages[0]["content"] %}
|
| 40 |
+
{%- set loop_messages = messages[1:] %}
|
| 41 |
+
{%- else %}
|
| 42 |
+
{%- set loop_messages = messages %}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{%- set ns = namespace(last_user_index=-1, assistant_is_last=false) %}
|
| 45 |
+
{%- for m in loop_messages %}
|
| 46 |
+
{%- if m.role == 'user' %}
|
| 47 |
+
{%- set ns.last_user_index = loop.index0 -%}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- endfor %}
|
| 50 |
+
{%- if not tools is defined %}
|
| 51 |
+
{%- set tools = [] %}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- set has_system = false %}
|
| 54 |
+
{%- if system_message is defined %}
|
| 55 |
+
{{- "<|im_start|>system\n" + system_message }}
|
| 56 |
+
{%- set has_system = true %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 59 |
+
{%- if not has_system %}
|
| 60 |
+
{{- "<|im_start|>system\n" }}
|
| 61 |
+
{%- set has_system = true %}
|
| 62 |
+
{%- endif %}
|
| 63 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou have access to the following functions:\n\n" }}
|
| 64 |
+
{{- "<tools>" }}
|
| 65 |
+
{%- for tool in tools %}
|
| 66 |
+
{%- if tool.function is defined %}
|
| 67 |
+
{%- set tool = tool.function %}
|
| 68 |
+
{%- endif %}
|
| 69 |
+
{{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
|
| 70 |
+
{%- if tool.description is defined %}
|
| 71 |
+
{{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{{- '\n<parameters>' }}
|
| 74 |
+
{%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
|
| 75 |
+
{%- for param_name, param_fields in tool.parameters.properties|items %}
|
| 76 |
+
{{- '\n<parameter>' }}
|
| 77 |
+
{{- '\n<name>' ~ param_name ~ '</name>' }}
|
| 78 |
+
{%- if param_fields.type is defined %}
|
| 79 |
+
{{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- if param_fields.description is defined %}
|
| 82 |
+
{{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
|
| 83 |
+
{%- endif %}
|
| 84 |
+
{%- set handled_keys = ['name', 'type', 'description'] %}
|
| 85 |
+
{{- render_extra_keys(param_fields, handled_keys) }}
|
| 86 |
+
{{- '\n</parameter>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- set handled_keys = ['type', 'properties'] %}
|
| 90 |
+
{{- render_extra_keys(tool.parameters, handled_keys) }}
|
| 91 |
+
{{- '\n</parameters>' }}
|
| 92 |
+
{%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
|
| 93 |
+
{{- render_extra_keys(tool, handled_keys) }}
|
| 94 |
+
{{- '\n</function>' }}
|
| 95 |
+
{%- endfor %}
|
| 96 |
+
{{- "\n</tools>" }}
|
| 97 |
+
{{- '\n\nFor each function call, output the function name and arguments in the following format:\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>value_1</parameter>\n<parameter=example_parameter_2>This is the value for the second parameter\nthat can span\nmultiple lines</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- DO NOT use function calls inside <think></think> tags.\n- The value enclosed between parameter tags is preserved exactly as-is, including newlines and spaces.\n</IMPORTANT>' }}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- if has_system %}
|
| 100 |
+
{{- '<|im_end|>\n' }}
|
| 101 |
+
{%- endif %}
|
| 102 |
+
{%- for message in loop_messages %}
|
| 103 |
+
{%- if message.content is string %}
|
| 104 |
+
{%- set content = message.content %}
|
| 105 |
+
{%- else %}
|
| 106 |
+
{%- set content = render_content(message.content) %}
|
| 107 |
+
{%- endif %}
|
| 108 |
+
{%- if message.role == "assistant" %}
|
| 109 |
+
{%- if message.reasoning_content is string %}
|
| 110 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 111 |
+
{%- else %}
|
| 112 |
+
{%- set reasoning_content = '' %}
|
| 113 |
+
{%- if '</think>' in content %}
|
| 114 |
+
{%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
|
| 115 |
+
{%- set content = content.split('</think>')[-1] %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endif %}
|
| 118 |
+
{%- if (keep_all_reasoning or loop.index0 > ns.last_user_index) and reasoning_content -%}
|
| 119 |
+
{{- '<|im_start|>' + message.role + '\n<think>' + reasoning_content + '</think>' + content }}
|
| 120 |
+
{%- else %}
|
| 121 |
+
{{- '<|im_start|>' + message.role + '\n<think></think>' + content }}
|
| 122 |
+
{%- endif %}
|
| 123 |
+
{%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
|
| 124 |
+
{%- for tool_call in message.tool_calls %}
|
| 125 |
+
{%- if tool_call.function is defined %}
|
| 126 |
+
{%- set tool_call = tool_call.function %}
|
| 127 |
+
{%- endif %}
|
| 128 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 129 |
+
{%- if tool_call.arguments is defined %}
|
| 130 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 131 |
+
{{- '<parameter=' + args_name + '>' }}
|
| 132 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 133 |
+
{{- args_value }}
|
| 134 |
+
{{- '</parameter>\n' }}
|
| 135 |
+
{%- endfor %}
|
| 136 |
+
{%- endif %}
|
| 137 |
+
{{- '</function>\n</tool_call>' }}
|
| 138 |
+
{%- endfor %}
|
| 139 |
+
{%- endif %}
|
| 140 |
+
{%- if loop.last %}
|
| 141 |
+
{%- set ns.assistant_is_last = true %}
|
| 142 |
+
{%- else %}
|
| 143 |
+
{{- '<|im_end|>\n' }}
|
| 144 |
+
{%- endif %}
|
| 145 |
+
{%- elif message.role == "user" %}
|
| 146 |
+
{{- '<|im_start|>' + message.role + '\n' + render_content(message.content) + '<|im_end|>\n' }}
|
| 147 |
+
{%- elif message.role == "system" %}
|
| 148 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
| 149 |
+
{%- elif message.role == "tool" %}
|
| 150 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 151 |
+
{{- '<|im_start|>tool\n' }}
|
| 152 |
+
{%- endif %}
|
| 153 |
+
{{- '<tool_response>\n' }}
|
| 154 |
+
{{- render_content(message.content) }}
|
| 155 |
+
{{- '\n</tool_response>\n' }}
|
| 156 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 157 |
+
{{- '<|im_end|>\n' }}
|
| 158 |
+
{%- elif loop.last %}
|
| 159 |
+
{{- '<|im_end|>\n' }}
|
| 160 |
+
{%- endif %}
|
| 161 |
+
{%- else %}
|
| 162 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
| 163 |
+
{%- endif %}
|
| 164 |
+
{%- endfor %}
|
| 165 |
+
{%- if add_generation_prompt and not ns.assistant_is_last %}
|
| 166 |
+
{{- '<|im_start|>assistant\n' }}
|
| 167 |
+
{%- if not enable_thinking -%}
|
| 168 |
+
{{- '<think>\n\n</think>\n' -}}
|
| 169 |
+
{%- endif -%}
|
| 170 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_input_local_transformer": true,
|
| 3 |
+
"add_speech_sosp_eosp": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"MiMoV2ASRForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": true,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"audio_channels": 8,
|
| 10 |
+
"delay_pattern": "0-1-2-3-4-5-6-7",
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"empty_loss_weight": 0.01,
|
| 13 |
+
"group_size": 4,
|
| 14 |
+
"head_dim": 128,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 4096,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"input_full_attention": true,
|
| 19 |
+
"input_local_dim": 1024,
|
| 20 |
+
"input_local_layers": 6,
|
| 21 |
+
"intermediate_size": 11008,
|
| 22 |
+
"layer_types": [
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention"
|
| 59 |
+
],
|
| 60 |
+
"local_attn_dropout": 0.1,
|
| 61 |
+
"local_attn_heads": 64,
|
| 62 |
+
"local_dim": 1024,
|
| 63 |
+
"local_ffn_dim": 4096,
|
| 64 |
+
"local_hidden_dropout": 0.1,
|
| 65 |
+
"local_layers": 16,
|
| 66 |
+
"local_rotary_base": 640000,
|
| 67 |
+
"max_position_embeddings": 8192,
|
| 68 |
+
"max_window_layers": 28,
|
| 69 |
+
"mlp_layers": 1,
|
| 70 |
+
"model_type": "qwen2",
|
| 71 |
+
"n_rvq": 20,
|
| 72 |
+
"no_speech_loss": false,
|
| 73 |
+
"no_text_loss": false,
|
| 74 |
+
"num_attention_heads": 32,
|
| 75 |
+
"num_hidden_layers": 36,
|
| 76 |
+
"num_key_value_heads": 8,
|
| 77 |
+
"rms_norm_eps": 1e-06,
|
| 78 |
+
"rope_scaling": null,
|
| 79 |
+
"rope_theta": 640000,
|
| 80 |
+
"sliding_window": null,
|
| 81 |
+
"speech_vocab_size": "1025-1025-129-129-129-129-129-129",
|
| 82 |
+
"speech_zeroemb_idx": "1024-1024-128-128-128-128-128-128",
|
| 83 |
+
"tie_word_embeddings": false,
|
| 84 |
+
"transformers_version": "4.57.1",
|
| 85 |
+
"use_cache": true,
|
| 86 |
+
"use_sliding_window": false,
|
| 87 |
+
"vocab_size": 151680,
|
| 88 |
+
"audio_config": {
|
| 89 |
+
"tokenizer_version": "v1",
|
| 90 |
+
"speech_vocab_size": "1025-1025-129-129-129-129-129-129",
|
| 91 |
+
"speech_zeroemb_idx": "1024-1024-128-128-128-128-128-128",
|
| 92 |
+
"group_size": 4,
|
| 93 |
+
"audio_channels": 8,
|
| 94 |
+
"input_local_layers": 6,
|
| 95 |
+
"input_local_dim": 1024,
|
| 96 |
+
"input_full_attention": true,
|
| 97 |
+
"input_local_attn_heads": 64,
|
| 98 |
+
"input_local_head_dim": 16,
|
| 99 |
+
"input_local_intermediate_size": 4096,
|
| 100 |
+
"input_local_hidden_dropout": 0.1,
|
| 101 |
+
"out_hidden_size": 4096,
|
| 102 |
+
"rope_theta": 640000,
|
| 103 |
+
"partial_rotary_factor": 1.0,
|
| 104 |
+
"projection_layers": 1,
|
| 105 |
+
"add_post_norm": true,
|
| 106 |
+
"audio_segment_size": 6000
|
| 107 |
+
}
|
| 108 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"temperature": 0.6,
|
| 4 |
+
"top_k": -1,
|
| 5 |
+
"top_p": 0.95
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e424db00a4258cf62b626d4bab42627d619d537d9ae975bae54591b1bbb25ae
|
| 3 |
+
size 4959966216
|
model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d83ee8aab141033fdb77a4d52d1bcd839247007198159f71f6b61db809e9987e
|
| 3 |
+
size 4962272576
|
model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:409d6d66d78ab50bddfa02af7108a1486c8018fb00231f62a4ea14c594a57a24
|
| 3 |
+
size 4962272648
|
model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8bb46073f13a61b39249787668f69222ab5e76fecd1240604ecff1e5b0251b9
|
| 3 |
+
size 4962272648
|
model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8aa4249ee58a1762187a589f2fb0053cc9d2833ef3beb5cefc75075d227dfca
|
| 3 |
+
size 4962272648
|
model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cecc940b16d122e807859cf919deceb2d3a9ac1668b27b876252e20293117b0c
|
| 3 |
+
size 3196344216
|
model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf197fef74fa019c2567e6b4d054a0335fd15234ddd7c9b891a303a7102e031b
|
| 3 |
+
size 4069034792
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,727 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 7622619136,
|
| 4 |
+
"total_size": 32074350592
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"hidden_states_downcast.weight": "model-00007-of-00007.safetensors",
|
| 8 |
+
"input_local_transformer.layers.0.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 9 |
+
"input_local_transformer.layers.0.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 10 |
+
"input_local_transformer.layers.0.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 11 |
+
"input_local_transformer.layers.0.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 12 |
+
"input_local_transformer.layers.0.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 13 |
+
"input_local_transformer.layers.0.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 14 |
+
"input_local_transformer.layers.0.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 15 |
+
"input_local_transformer.layers.0.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 16 |
+
"input_local_transformer.layers.0.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 17 |
+
"input_local_transformer.layers.0.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 18 |
+
"input_local_transformer.layers.0.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 19 |
+
"input_local_transformer.layers.0.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 20 |
+
"input_local_transformer.layers.1.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 21 |
+
"input_local_transformer.layers.1.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 22 |
+
"input_local_transformer.layers.1.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 23 |
+
"input_local_transformer.layers.1.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 24 |
+
"input_local_transformer.layers.1.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 25 |
+
"input_local_transformer.layers.1.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 26 |
+
"input_local_transformer.layers.1.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 27 |
+
"input_local_transformer.layers.1.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 28 |
+
"input_local_transformer.layers.1.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 29 |
+
"input_local_transformer.layers.1.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 30 |
+
"input_local_transformer.layers.1.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 31 |
+
"input_local_transformer.layers.1.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 32 |
+
"input_local_transformer.layers.2.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 33 |
+
"input_local_transformer.layers.2.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 34 |
+
"input_local_transformer.layers.2.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 35 |
+
"input_local_transformer.layers.2.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 36 |
+
"input_local_transformer.layers.2.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 37 |
+
"input_local_transformer.layers.2.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 38 |
+
"input_local_transformer.layers.2.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 39 |
+
"input_local_transformer.layers.2.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 40 |
+
"input_local_transformer.layers.2.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 41 |
+
"input_local_transformer.layers.2.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 42 |
+
"input_local_transformer.layers.2.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 43 |
+
"input_local_transformer.layers.2.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 44 |
+
"input_local_transformer.layers.3.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 45 |
+
"input_local_transformer.layers.3.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 46 |
+
"input_local_transformer.layers.3.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 47 |
+
"input_local_transformer.layers.3.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 48 |
+
"input_local_transformer.layers.3.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 49 |
+
"input_local_transformer.layers.3.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 50 |
+
"input_local_transformer.layers.3.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 51 |
+
"input_local_transformer.layers.3.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 52 |
+
"input_local_transformer.layers.3.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 53 |
+
"input_local_transformer.layers.3.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 54 |
+
"input_local_transformer.layers.3.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 55 |
+
"input_local_transformer.layers.3.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 56 |
+
"input_local_transformer.layers.4.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 57 |
+
"input_local_transformer.layers.4.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 58 |
+
"input_local_transformer.layers.4.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 59 |
+
"input_local_transformer.layers.4.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 60 |
+
"input_local_transformer.layers.4.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 61 |
+
"input_local_transformer.layers.4.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 62 |
+
"input_local_transformer.layers.4.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 63 |
+
"input_local_transformer.layers.4.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 64 |
+
"input_local_transformer.layers.4.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 65 |
+
"input_local_transformer.layers.4.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 66 |
+
"input_local_transformer.layers.4.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 67 |
+
"input_local_transformer.layers.4.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 68 |
+
"input_local_transformer.layers.5.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 69 |
+
"input_local_transformer.layers.5.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 70 |
+
"input_local_transformer.layers.5.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 71 |
+
"input_local_transformer.layers.5.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 72 |
+
"input_local_transformer.layers.5.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 73 |
+
"input_local_transformer.layers.5.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 74 |
+
"input_local_transformer.layers.5.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 75 |
+
"input_local_transformer.layers.5.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 76 |
+
"input_local_transformer.layers.5.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 77 |
+
"input_local_transformer.layers.5.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 78 |
+
"input_local_transformer.layers.5.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 79 |
+
"input_local_transformer.layers.5.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 80 |
+
"input_local_transformer.norm.weight": "model-00007-of-00007.safetensors",
|
| 81 |
+
"lm_head.weight": "model-00007-of-00007.safetensors",
|
| 82 |
+
"local_transformer.layers.0.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 83 |
+
"local_transformer.layers.0.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 84 |
+
"local_transformer.layers.0.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 85 |
+
"local_transformer.layers.0.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 86 |
+
"local_transformer.layers.0.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 87 |
+
"local_transformer.layers.0.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 88 |
+
"local_transformer.layers.0.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 89 |
+
"local_transformer.layers.0.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 90 |
+
"local_transformer.layers.0.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 91 |
+
"local_transformer.layers.0.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 92 |
+
"local_transformer.layers.0.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 93 |
+
"local_transformer.layers.0.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 94 |
+
"local_transformer.layers.1.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 95 |
+
"local_transformer.layers.1.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 96 |
+
"local_transformer.layers.1.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 97 |
+
"local_transformer.layers.1.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 98 |
+
"local_transformer.layers.1.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 99 |
+
"local_transformer.layers.1.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 100 |
+
"local_transformer.layers.1.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 101 |
+
"local_transformer.layers.1.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 102 |
+
"local_transformer.layers.1.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 103 |
+
"local_transformer.layers.1.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 104 |
+
"local_transformer.layers.1.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 105 |
+
"local_transformer.layers.1.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 106 |
+
"local_transformer.layers.10.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 107 |
+
"local_transformer.layers.10.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 108 |
+
"local_transformer.layers.10.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 109 |
+
"local_transformer.layers.10.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 110 |
+
"local_transformer.layers.10.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 111 |
+
"local_transformer.layers.10.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 112 |
+
"local_transformer.layers.10.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 113 |
+
"local_transformer.layers.10.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 114 |
+
"local_transformer.layers.10.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 115 |
+
"local_transformer.layers.10.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 116 |
+
"local_transformer.layers.10.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 117 |
+
"local_transformer.layers.10.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 118 |
+
"local_transformer.layers.11.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 119 |
+
"local_transformer.layers.11.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 120 |
+
"local_transformer.layers.11.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 121 |
+
"local_transformer.layers.11.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 122 |
+
"local_transformer.layers.11.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 123 |
+
"local_transformer.layers.11.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 124 |
+
"local_transformer.layers.11.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 125 |
+
"local_transformer.layers.11.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 126 |
+
"local_transformer.layers.11.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 127 |
+
"local_transformer.layers.11.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 128 |
+
"local_transformer.layers.11.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 129 |
+
"local_transformer.layers.11.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 130 |
+
"local_transformer.layers.12.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 131 |
+
"local_transformer.layers.12.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 132 |
+
"local_transformer.layers.12.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 133 |
+
"local_transformer.layers.12.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 134 |
+
"local_transformer.layers.12.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 135 |
+
"local_transformer.layers.12.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 136 |
+
"local_transformer.layers.12.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 137 |
+
"local_transformer.layers.12.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 138 |
+
"local_transformer.layers.12.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 139 |
+
"local_transformer.layers.12.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 140 |
+
"local_transformer.layers.12.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 141 |
+
"local_transformer.layers.12.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 142 |
+
"local_transformer.layers.13.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 143 |
+
"local_transformer.layers.13.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 144 |
+
"local_transformer.layers.13.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 145 |
+
"local_transformer.layers.13.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 146 |
+
"local_transformer.layers.13.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 147 |
+
"local_transformer.layers.13.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 148 |
+
"local_transformer.layers.13.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 149 |
+
"local_transformer.layers.13.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 150 |
+
"local_transformer.layers.13.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 151 |
+
"local_transformer.layers.13.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 152 |
+
"local_transformer.layers.13.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 153 |
+
"local_transformer.layers.13.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 154 |
+
"local_transformer.layers.14.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 155 |
+
"local_transformer.layers.14.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 156 |
+
"local_transformer.layers.14.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 157 |
+
"local_transformer.layers.14.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 158 |
+
"local_transformer.layers.14.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 159 |
+
"local_transformer.layers.14.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 160 |
+
"local_transformer.layers.14.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 161 |
+
"local_transformer.layers.14.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 162 |
+
"local_transformer.layers.14.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 163 |
+
"local_transformer.layers.14.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 164 |
+
"local_transformer.layers.14.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 165 |
+
"local_transformer.layers.14.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 166 |
+
"local_transformer.layers.15.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 167 |
+
"local_transformer.layers.15.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 168 |
+
"local_transformer.layers.15.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 169 |
+
"local_transformer.layers.15.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 170 |
+
"local_transformer.layers.15.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 171 |
+
"local_transformer.layers.15.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 172 |
+
"local_transformer.layers.15.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 173 |
+
"local_transformer.layers.15.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 174 |
+
"local_transformer.layers.15.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 175 |
+
"local_transformer.layers.15.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 176 |
+
"local_transformer.layers.15.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 177 |
+
"local_transformer.layers.15.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 178 |
+
"local_transformer.layers.2.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 179 |
+
"local_transformer.layers.2.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 180 |
+
"local_transformer.layers.2.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 181 |
+
"local_transformer.layers.2.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 182 |
+
"local_transformer.layers.2.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 183 |
+
"local_transformer.layers.2.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 184 |
+
"local_transformer.layers.2.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 185 |
+
"local_transformer.layers.2.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 186 |
+
"local_transformer.layers.2.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 187 |
+
"local_transformer.layers.2.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 188 |
+
"local_transformer.layers.2.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 189 |
+
"local_transformer.layers.2.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 190 |
+
"local_transformer.layers.3.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 191 |
+
"local_transformer.layers.3.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 192 |
+
"local_transformer.layers.3.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 193 |
+
"local_transformer.layers.3.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 194 |
+
"local_transformer.layers.3.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 195 |
+
"local_transformer.layers.3.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 196 |
+
"local_transformer.layers.3.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 197 |
+
"local_transformer.layers.3.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 198 |
+
"local_transformer.layers.3.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 199 |
+
"local_transformer.layers.3.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 200 |
+
"local_transformer.layers.3.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 201 |
+
"local_transformer.layers.3.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 202 |
+
"local_transformer.layers.4.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 203 |
+
"local_transformer.layers.4.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 204 |
+
"local_transformer.layers.4.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 205 |
+
"local_transformer.layers.4.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 206 |
+
"local_transformer.layers.4.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 207 |
+
"local_transformer.layers.4.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 208 |
+
"local_transformer.layers.4.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 209 |
+
"local_transformer.layers.4.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 210 |
+
"local_transformer.layers.4.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 211 |
+
"local_transformer.layers.4.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 212 |
+
"local_transformer.layers.4.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 213 |
+
"local_transformer.layers.4.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 214 |
+
"local_transformer.layers.5.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 215 |
+
"local_transformer.layers.5.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 216 |
+
"local_transformer.layers.5.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 217 |
+
"local_transformer.layers.5.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 218 |
+
"local_transformer.layers.5.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 219 |
+
"local_transformer.layers.5.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 220 |
+
"local_transformer.layers.5.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 221 |
+
"local_transformer.layers.5.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 222 |
+
"local_transformer.layers.5.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 223 |
+
"local_transformer.layers.5.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 224 |
+
"local_transformer.layers.5.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 225 |
+
"local_transformer.layers.5.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 226 |
+
"local_transformer.layers.6.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 227 |
+
"local_transformer.layers.6.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 228 |
+
"local_transformer.layers.6.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 229 |
+
"local_transformer.layers.6.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 230 |
+
"local_transformer.layers.6.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 231 |
+
"local_transformer.layers.6.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 232 |
+
"local_transformer.layers.6.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 233 |
+
"local_transformer.layers.6.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 234 |
+
"local_transformer.layers.6.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 235 |
+
"local_transformer.layers.6.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 236 |
+
"local_transformer.layers.6.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 237 |
+
"local_transformer.layers.6.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 238 |
+
"local_transformer.layers.7.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 239 |
+
"local_transformer.layers.7.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 240 |
+
"local_transformer.layers.7.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 241 |
+
"local_transformer.layers.7.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 242 |
+
"local_transformer.layers.7.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 243 |
+
"local_transformer.layers.7.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 244 |
+
"local_transformer.layers.7.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 245 |
+
"local_transformer.layers.7.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 246 |
+
"local_transformer.layers.7.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 247 |
+
"local_transformer.layers.7.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 248 |
+
"local_transformer.layers.7.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 249 |
+
"local_transformer.layers.7.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 250 |
+
"local_transformer.layers.8.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 251 |
+
"local_transformer.layers.8.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 252 |
+
"local_transformer.layers.8.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 253 |
+
"local_transformer.layers.8.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 254 |
+
"local_transformer.layers.8.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 255 |
+
"local_transformer.layers.8.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 256 |
+
"local_transformer.layers.8.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 257 |
+
"local_transformer.layers.8.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 258 |
+
"local_transformer.layers.8.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 259 |
+
"local_transformer.layers.8.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 260 |
+
"local_transformer.layers.8.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 261 |
+
"local_transformer.layers.8.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 262 |
+
"local_transformer.layers.9.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 263 |
+
"local_transformer.layers.9.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 264 |
+
"local_transformer.layers.9.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 265 |
+
"local_transformer.layers.9.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 266 |
+
"local_transformer.layers.9.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 267 |
+
"local_transformer.layers.9.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 268 |
+
"local_transformer.layers.9.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 269 |
+
"local_transformer.layers.9.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 270 |
+
"local_transformer.layers.9.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 271 |
+
"local_transformer.layers.9.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 272 |
+
"local_transformer.layers.9.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 273 |
+
"local_transformer.layers.9.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 274 |
+
"local_transformer.norm.weight": "model-00007-of-00007.safetensors",
|
| 275 |
+
"local_transformer_lm_heads.0.weight": "model-00007-of-00007.safetensors",
|
| 276 |
+
"local_transformer_lm_heads.1.weight": "model-00007-of-00007.safetensors",
|
| 277 |
+
"local_transformer_lm_heads.2.weight": "model-00007-of-00007.safetensors",
|
| 278 |
+
"local_transformer_lm_heads.3.weight": "model-00007-of-00007.safetensors",
|
| 279 |
+
"local_transformer_lm_heads.4.weight": "model-00007-of-00007.safetensors",
|
| 280 |
+
"local_transformer_lm_heads.5.weight": "model-00007-of-00007.safetensors",
|
| 281 |
+
"local_transformer_lm_heads.6.weight": "model-00007-of-00007.safetensors",
|
| 282 |
+
"local_transformer_lm_heads.7.weight": "model-00007-of-00007.safetensors",
|
| 283 |
+
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
| 284 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 285 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 286 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 287 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 288 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 289 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 290 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 291 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 292 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 293 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 294 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 295 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 296 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 297 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 298 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 299 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 300 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 301 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 302 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 303 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 304 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 305 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 306 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 307 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 308 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 309 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 310 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 311 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 312 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 313 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 314 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 315 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 316 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 317 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 318 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 319 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 320 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 321 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 322 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 323 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 324 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 325 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 326 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 327 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 328 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 329 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 330 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 331 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 332 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 333 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 334 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 335 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 336 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 337 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 338 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 339 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 340 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 341 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 342 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 343 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 344 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 345 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 346 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 347 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 348 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 349 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 350 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 351 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 352 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 353 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 354 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 355 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 356 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 357 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 358 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 359 |
+
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 360 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 361 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 362 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 363 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 364 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 365 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 366 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 367 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 368 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 369 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 370 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 371 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 372 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 373 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 374 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 375 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 376 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 377 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 378 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 379 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 380 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 381 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 382 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 383 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 384 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 385 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 386 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 387 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 388 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 389 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 390 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 391 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 392 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 393 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 394 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 395 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 396 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 397 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 398 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 399 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 400 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 401 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 402 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 403 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 404 |
+
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 405 |
+
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 406 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 407 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 408 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 409 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 410 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 411 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 412 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 413 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 414 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 415 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 416 |
+
"model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 417 |
+
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 418 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 419 |
+
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 420 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 421 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 422 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 423 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 424 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 425 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 426 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 427 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 428 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 429 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 430 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 431 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 432 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 433 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 434 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 435 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 436 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 437 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 438 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 439 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 440 |
+
"model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 441 |
+
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 442 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 443 |
+
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 444 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 445 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 446 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 447 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 448 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 449 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 450 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 451 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 452 |
+
"model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 453 |
+
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 454 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 455 |
+
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 456 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 457 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 458 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 459 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 460 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 461 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 462 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 463 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 464 |
+
"model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 465 |
+
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 466 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 467 |
+
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 468 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 469 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 470 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 471 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 472 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 473 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 474 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 475 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 476 |
+
"model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 477 |
+
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 478 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 479 |
+
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 480 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 481 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 482 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 483 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 484 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 485 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 486 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 487 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 488 |
+
"model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 489 |
+
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 490 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 491 |
+
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 492 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 493 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 494 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 495 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 496 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 497 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 498 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 499 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 500 |
+
"model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 501 |
+
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 502 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 503 |
+
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 504 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 505 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 506 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 507 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 508 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 509 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 510 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 511 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 512 |
+
"model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 513 |
+
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 514 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 515 |
+
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 516 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 517 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 518 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 519 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 520 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 521 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 522 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 523 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 524 |
+
"model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 525 |
+
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 526 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 527 |
+
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 528 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 529 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 530 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 531 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 532 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 533 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 534 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 535 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 536 |
+
"model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 537 |
+
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 538 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 539 |
+
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 540 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 541 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 542 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 543 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 544 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 545 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 546 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 547 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 548 |
+
"model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 549 |
+
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 550 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 551 |
+
"model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 552 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 553 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 554 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 555 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 556 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 557 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 558 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 559 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 560 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 561 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 562 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 563 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 564 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 565 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 566 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 567 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 568 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 569 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 570 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 571 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 572 |
+
"model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 573 |
+
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 574 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 575 |
+
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 576 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 577 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 578 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 579 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 580 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 581 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 582 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 583 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 584 |
+
"model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 585 |
+
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 586 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 587 |
+
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 588 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 589 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 590 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 591 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 592 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 593 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 594 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 595 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 596 |
+
"model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 597 |
+
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 598 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 599 |
+
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 600 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 601 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 602 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 603 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 604 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 605 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 606 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 607 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 608 |
+
"model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 609 |
+
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 610 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 611 |
+
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 612 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 613 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 614 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 615 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 616 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 617 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 618 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 619 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 620 |
+
"model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 621 |
+
"model.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 622 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 623 |
+
"model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 624 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 625 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 626 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 627 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 628 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 629 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 630 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 631 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 632 |
+
"model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 633 |
+
"model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 634 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 635 |
+
"model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 636 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 637 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 638 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 639 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 640 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 641 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 642 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 643 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 644 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 645 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 646 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 647 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 648 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 649 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 650 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 651 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 652 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 653 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 654 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 655 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 656 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 657 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 658 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 659 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 660 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 661 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 662 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 663 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 664 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 665 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 666 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 667 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 668 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 669 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 670 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 671 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 672 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 673 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 674 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 675 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 676 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 677 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 678 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 679 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 680 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 681 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 682 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 683 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 684 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 685 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 686 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 687 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 688 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 689 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 690 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 691 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 692 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 693 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 694 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 695 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 696 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 697 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 698 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 699 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 700 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 701 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 702 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 703 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 704 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 705 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 706 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 707 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 708 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 709 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 710 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 711 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 712 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 713 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 714 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 715 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 716 |
+
"model.norm.weight": "model-00006-of-00007.safetensors",
|
| 717 |
+
"speech_embeddings.0.weight": "model-00007-of-00007.safetensors",
|
| 718 |
+
"speech_embeddings.1.weight": "model-00007-of-00007.safetensors",
|
| 719 |
+
"speech_embeddings.2.weight": "model-00007-of-00007.safetensors",
|
| 720 |
+
"speech_embeddings.3.weight": "model-00007-of-00007.safetensors",
|
| 721 |
+
"speech_embeddings.4.weight": "model-00007-of-00007.safetensors",
|
| 722 |
+
"speech_embeddings.5.weight": "model-00007-of-00007.safetensors",
|
| 723 |
+
"speech_embeddings.6.weight": "model-00007-of-00007.safetensors",
|
| 724 |
+
"speech_embeddings.7.weight": "model-00007-of-00007.safetensors",
|
| 725 |
+
"speech_group_downcast.weight": "model-00007-of-00007.safetensors"
|
| 726 |
+
}
|
| 727 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d91a78cce6441fd6855038f6764fc5f811ae949d9b89f43ac326cddfe91c66db
|
| 3 |
+
size 11423383
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,271 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<|sosp|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "<|eosp|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<|empty|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "<|Human|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
"151669": {
|
| 214 |
+
"content": "<|SpeechLM|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"151670": {
|
| 222 |
+
"content": "<|sostm|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"151671": {
|
| 230 |
+
"content": "<|eostm|>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"151672": {
|
| 238 |
+
"content": "<|eot|>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
}
|
| 245 |
+
},
|
| 246 |
+
"additional_special_tokens": [
|
| 247 |
+
"<|im_start|>",
|
| 248 |
+
"<|im_end|>",
|
| 249 |
+
"<|object_ref_start|>",
|
| 250 |
+
"<|object_ref_end|>",
|
| 251 |
+
"<|box_start|>",
|
| 252 |
+
"<|box_end|>",
|
| 253 |
+
"<|quad_start|>",
|
| 254 |
+
"<|quad_end|>",
|
| 255 |
+
"<|vision_start|>",
|
| 256 |
+
"<|vision_end|>",
|
| 257 |
+
"<|vision_pad|>",
|
| 258 |
+
"<|image_pad|>",
|
| 259 |
+
"<|video_pad|>"
|
| 260 |
+
],
|
| 261 |
+
"bos_token": null,
|
| 262 |
+
"clean_up_tokenization_spaces": false,
|
| 263 |
+
"eos_token": "<|im_end|>",
|
| 264 |
+
"errors": "replace",
|
| 265 |
+
"extra_special_tokens": {},
|
| 266 |
+
"model_max_length": 131072,
|
| 267 |
+
"pad_token": "<|endoftext|>",
|
| 268 |
+
"split_special_tokens": false,
|
| 269 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 270 |
+
"unk_token": null
|
| 271 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|