Commit ·
149d7b6
0
Parent(s):
Initial release
Browse files- .gitattributes +40 -0
- README.md +409 -0
- assets/meralion_hf_comparison.png +3 -0
- assets/samples/1_cantonese.wav +3 -0
- assets/samples/2_hokkien.wav +3 -0
- assets/samples/3_codeswitch_tamil.wav +3 -0
- assets/samples/4_codeswitch_singlish.wav +0 -0
- config.json +98 -0
- configuration_meralion3.py +80 -0
- generation_config.json +10 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +788 -0
- modeling_meralion3.py +567 -0
- preprocessor_config.json +18 -0
- processing_meralion3.py +193 -0
- processor_config.json +11 -0
- special_tokens_map.json +34 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +2019 -0
.gitattributes
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
assets/meralion_hf_comparison.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
assets/samples/1_cantonese.wav filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
assets/samples/2_hokkien.wav filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
assets/samples/3_codeswitch_tamil.wav filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,409 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: automatic-speech-recognition
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- meralion3
|
| 6 |
+
- meralion
|
| 7 |
+
- audio
|
| 8 |
+
- asr
|
| 9 |
+
- southeast-asian
|
| 10 |
+
- code-switching
|
| 11 |
+
language:
|
| 12 |
+
- en
|
| 13 |
+
- zh
|
| 14 |
+
- ms
|
| 15 |
+
- ta
|
| 16 |
+
- id
|
| 17 |
+
- th
|
| 18 |
+
- vi
|
| 19 |
+
- yue
|
| 20 |
+
- nan
|
| 21 |
+
arxiv:
|
| 22 |
+
- 2412.09818
|
| 23 |
+
- 2501.01034
|
| 24 |
+
- 2409.06635
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
# MERaLiON-3-ASR
|
| 28 |
+
|
| 29 |
+
**MERaLiON-3-ASR** is the speech-recognition line in the MERaLiON-3 generation of Speech-Text Large Language Models, developed by I2R, A\*STAR, Singapore. It is purpose-built for Singapore- and Southeast-Asia-centric ASR, with broad coverage across regional languages, dialects, and natural conversational code-switching.
|
| 30 |
+
|
| 31 |
+
**Coverage**
|
| 32 |
+
|
| 33 |
+
- **Languages:** English (Global and Singapore), Mandarin, Malay, Tamil, Indonesian, Thai, Vietnamese
|
| 34 |
+
- **Chinese dialects:** Cantonese, Hokkien
|
| 35 |
+
- **Code-switching:** natural conversational English ↔ {Mandarin, Malay, Tamil, Vietnamese, Cantonese, Hokkien} mixtures, including Singlish
|
| 36 |
+
|
| 37 |
+
## MERaLiON-3-ASR-API
|
| 38 |
+
|
| 39 |
+
**MERaLiON-3-ASR-API** is the hosted production endpoint, tuned for real-time and enterprise transcription workloads.
|
| 40 |
+
|
| 41 |
+
- **Fast streaming ASR**, ~600 ms first-token latency for interactive use cases.
|
| 42 |
+
- **Long-form decoding** for continuous audio up to multiple hours.
|
| 43 |
+
- **Word- and segment-level timestamps** with **speaker diarization** for offline transcription.
|
| 44 |
+
- **Reinforced regional-dialect recognition** for Cantonese and Hokkien.
|
| 45 |
+
- **State-of-the-art Southeast Asian code-switching** performance.
|
| 46 |
+
|
| 47 |
+
On the locked evaluation suite, MERaLiON-3-ASR-API achieves the lowest mean Word Error Rate among all systems tested on English (Singapore) (12.52, vs. 25.97 / 27.34 for Gemini 3.5 Flash / GPT-4o), Cantonese (10.42, best of all systems), Hokkien (36.43, vs. 46.50 next best), and Code-switching (20.87, vs. 22.65 / 31.14). On Healthcare it is statistically tied with Gemini 3.5 Flash (20.47 vs. 20.04, within 0.5 pp).
|
| 48 |
+
|
| 49 |
+
## MERaLiON-3-3B-ASR
|
| 50 |
+
|
| 51 |
+
**MERaLiON-3-3B-ASR** is the open-weights release published in this repository. At roughly one-third the size of its predecessor MERaLiON-2-10B-ASR, it matches or improves over the larger model on every evaluation section, with the largest gains concentrated where they matter most for the Southeast Asian setting:
|
| 52 |
+
|
| 53 |
+
| Section | MERaLiON-2-10B-ASR | MERaLiON-3-3B-ASR | Δ (pp) |
|
| 54 |
+
|---|---:|---:|---:|
|
| 55 |
+
| Thai | 35.07 | **7.55** | **−27.5** |
|
| 56 |
+
| Hokkien | 59.32 | **46.50** | **−12.8** |
|
| 57 |
+
| Cantonese | 18.55 | **11.27** | **−7.3** |
|
| 58 |
+
| Code-switching | 26.24 | **22.65** | **−3.6** |
|
| 59 |
+
| Tamil | 28.29 | **25.83** | **−2.5** |
|
| 60 |
+
|
| 61 |
+
The smaller footprint makes the open model practical for self-hosting on a single 80 GB GPU.
|
| 62 |
+
|
| 63 |
+
## Performance
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
The figure reports mean Word Error Rate (lower is better) across twelve language and domain sections, covering 66 evaluation datasets in total. Datasets in the Healthcare and Code-switching sections also appear in their primary language section, so they contribute to both. The full per-dataset breakdown is at [SEA-SpeechBench](https://github.com/SEA-SpeechBench/SEA-SpeechBench).
|
| 68 |
+
|
| 69 |
+
The table below reports per-dataset Word/Character Error Rate (lower is better) for Cantonese and Hokkien — the two regional Chinese dialects where MERaLiON-3 shows its largest relative advantage. The best result on each row is highlighted.
|
| 70 |
+
|
| 71 |
+
<div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;max-width:1000px;margin:0 auto;padding:16px 0">
|
| 72 |
+
<table style="width:100%;border-collapse:collapse;font-size:13px">
|
| 73 |
+
<thead><tr>
|
| 74 |
+
<th style="padding:10px 7px;text-align:left;font-weight:600;border-bottom:2px solid #1e6f8b;color:#1e6f8b"></th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #1e6f8b;color:#1e6f8b;font-size:14px">MERaLiON-3-ASR-API</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #1e6f8b;color:#1e6f8b;font-size:14px">MERaLiON-3-3B-ASR</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #1e6f8b;color:#1e6f8b;font-size:14px">MERaLiON-2-10B-ASR</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #1e6f8b;color:#1e6f8b;font-size:14px">Qwen3-ASR</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #1e6f8b;color:#1e6f8b;font-size:14px">gpt-4o</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #1e6f8b;color:#1e6f8b;font-size:14px">gpt-audio-1.5</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #1e6f8b;color:#1e6f8b;font-size:14px">gemini-3.5-flash</th></tr></thead>
|
| 75 |
+
<tbody>
|
| 76 |
+
<tr><td colspan="8" style="padding:8px 12px;font-weight:600;color:#1e6f8b;border-bottom:1px solid rgba(30, 111, 139, 0.2);background:rgba(30, 111, 139, 0.10)">Cantonese</td></tr>
|
| 77 |
+
<tr>
|
| 78 |
+
<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">cv21_cantonese_test</td>
|
| 79 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">11.65</td>
|
| 80 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">13.88</td>
|
| 81 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">18.29</td>
|
| 82 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">25.08</td>
|
| 83 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;font-weight:700">8.74</td>
|
| 84 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">21.96</td>
|
| 85 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">20.34</td>
|
| 86 |
+
</tr>
|
| 87 |
+
<tr>
|
| 88 |
+
<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">fleurs_cantonese_test</td>
|
| 89 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">8.75</td>
|
| 90 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">8.93</td>
|
| 91 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">10.53</td>
|
| 92 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">11.30</td>
|
| 93 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;font-weight:700">6.31</td>
|
| 94 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">7.55</td>
|
| 95 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">9.63</td>
|
| 96 |
+
</tr>
|
| 97 |
+
<tr>
|
| 98 |
+
<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">mdcc_cantonese_test</td>
|
| 99 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;font-weight:700">4.95</td>
|
| 100 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">5.11</td>
|
| 101 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">6.95</td>
|
| 102 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">8.67</td>
|
| 103 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">7.56</td>
|
| 104 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">18.51</td>
|
| 105 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">11.27</td>
|
| 106 |
+
</tr>
|
| 107 |
+
<tr>
|
| 108 |
+
<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">wsyue_long_test</td>
|
| 109 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;font-weight:700">9.37</td>
|
| 110 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">9.76</td>
|
| 111 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">18.17</td>
|
| 112 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">11.66</td>
|
| 113 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">25.16</td>
|
| 114 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">29.59</td>
|
| 115 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">14.66</td>
|
| 116 |
+
</tr>
|
| 117 |
+
<tr>
|
| 118 |
+
<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">wsyue_short_test</td>
|
| 119 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;font-weight:700">11.19</td>
|
| 120 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">12.56</td>
|
| 121 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">24.55</td>
|
| 122 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">17.77</td>
|
| 123 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">18.23</td>
|
| 124 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">33.99</td>
|
| 125 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">31.01</td>
|
| 126 |
+
</tr>
|
| 127 |
+
<tr>
|
| 128 |
+
<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">ytb_asr_cantonese_short_v3</td>
|
| 129 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;font-weight:700">16.63</td>
|
| 130 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">17.38</td>
|
| 131 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">32.83</td>
|
| 132 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">16.92</td>
|
| 133 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">35.48</td>
|
| 134 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">38.66</td>
|
| 135 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">19.87</td>
|
| 136 |
+
</tr>
|
| 137 |
+
<tr><td colspan="8" style="padding:8px 12px;font-weight:600;color:#1e6f8b;border-bottom:1px solid rgba(30, 111, 139, 0.2);background:rgba(30, 111, 139, 0.10)">Hokkien</td></tr>
|
| 138 |
+
<tr>
|
| 139 |
+
<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">sarahwei_minnan_test</td>
|
| 140 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;font-weight:700">18.93</td>
|
| 141 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">22.58</td>
|
| 142 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">49.47</td>
|
| 143 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">66.17</td>
|
| 144 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">44.93</td>
|
| 145 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">77.26</td>
|
| 146 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">46.38</td>
|
| 147 |
+
</tr>
|
| 148 |
+
<tr>
|
| 149 |
+
<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">taiwan_tongues_hokkien_test</td>
|
| 150 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;font-weight:700">51.64</td>
|
| 151 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">58.64</td>
|
| 152 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">63.90</td>
|
| 153 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">99.05</td>
|
| 154 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">66.41</td>
|
| 155 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">109.41</td>
|
| 156 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">73.40</td>
|
| 157 |
+
</tr>
|
| 158 |
+
<tr>
|
| 159 |
+
<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">ytb_asr_hokkien_happycanalready_s4</td>
|
| 160 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;font-weight:700">38.72</td>
|
| 161 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">58.30</td>
|
| 162 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">64.58</td>
|
| 163 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">128.21</td>
|
| 164 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">78.89</td>
|
| 165 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">68.55</td>
|
| 166 |
+
<td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">63.37</td>
|
| 167 |
+
</tr>
|
| 168 |
+
</tbody>
|
| 169 |
+
</table>
|
| 170 |
+
</div>
|
| 171 |
+
|
| 172 |
+
### Qualitative examples
|
| 173 |
+
|
| 174 |
+
The four clips below illustrate cases where MERaLiON-3-ASR-API produces the most accurate transcript, MERaLiON-3-3B-ASR a near-equivalent transcript with one or two character-level differences, and a leading general-purpose model produces a substantially less faithful transcript.
|
| 175 |
+
|
| 176 |
+
<div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;max-width:1000px;margin:0 auto;padding:16px 0">
|
| 177 |
+
<h4 style="margin:18px 0 6px 0;color:#1e6f8b">Cantonese (with code-switching to English)</h4>
|
| 178 |
+
<audio controls preload="none" src="https://huggingface.co/MERaLiON/MERaLiON-3-3B-ASR/resolve/main/assets/samples/1_cantonese.wav" style="width:100%;max-width:520px"></audio>
|
| 179 |
+
<table style="width:100%;border-collapse:collapse;font-size:13px;margin:6px 0 4px 0">
|
| 180 |
+
<tbody>
|
| 181 |
+
<tr>
|
| 182 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#444;font-weight:600;width:170px;white-space:nowrap;vertical-align:top">Reference</td>
|
| 183 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">嚟我公司，In-house PR Director，有冇兴趣？ 哇，你问得咁直接，我唔怕直接答啊。</td>
|
| 184 |
+
</tr>
|
| 185 |
+
<tr>
|
| 186 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;;width:170px;white-space:nowrap;vertical-align:top">MERaLiON-3-ASR-API</td>
|
| 187 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">嚟我公司，in-house PR director，有冇兴趣？你问得咁直接，我又唔怕直接答啊。</td>
|
| 188 |
+
</tr>
|
| 189 |
+
<tr>
|
| 190 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#444;;width:170px;white-space:nowrap;vertical-align:top">MERaLiON-3-3B-ASR</td>
|
| 191 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">嚟我公司 in house p r director 有冇兴趣你问得咁直接我用唔怕直接答啊。</td>
|
| 192 |
+
</tr>
|
| 193 |
+
<tr>
|
| 194 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#888;;width:170px;white-space:nowrap;vertical-align:top">gemini-3.5-flash</td>
|
| 195 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">你間公司 In-house PR director 係咪呀？你問得咁直接，我好難直接答呀。</td>
|
| 196 |
+
</tr>
|
| 197 |
+
</tbody></table>
|
| 198 |
+
<h4 style="margin:18px 0 6px 0;color:#1e6f8b">Hokkien (with code-switching to English)</h4>
|
| 199 |
+
<audio controls preload="none" src="https://huggingface.co/MERaLiON/MERaLiON-3-3B-ASR/resolve/main/assets/samples/2_hokkien.wav" style="width:100%;max-width:520px"></audio>
|
| 200 |
+
<table style="width:100%;border-collapse:collapse;font-size:13px;margin:6px 0 4px 0">
|
| 201 |
+
<tbody>
|
| 202 |
+
<tr>
|
| 203 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#444;font-weight:600;width:170px;white-space:nowrap;vertical-align:top">Reference</td>
|
| 204 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">我……我……我新来的 recruit 啦！按怎无戴 helmet？ 我……我袂使戴！我一戴，人就认袂出是我了！哈哈哈！我是……我是 recruit 梁婆婆！哈哈哈！人夯 full pack，按怎汝无 full pack？ 有啊！我这个就是 full pack 啦！哈哈哈！</td>
|
| 205 |
+
</tr>
|
| 206 |
+
<tr>
|
| 207 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;;width:170px;white-space:nowrap;vertical-align:top">MERaLiON-3-ASR-API</td>
|
| 208 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">我啊，我是来 recruit 啊！安怎无带 helmet？我未使带，我一个带人欲啉袂出是我了！哈哈哈！我是、我是 recruit，梁某无！哈哈哈！人提 full pack，安怎汝无 full pack？我有啊！我即个就是 full pack 啊！哈哈哈！</td>
|
| 209 |
+
</tr>
|
| 210 |
+
<tr>
|
| 211 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#444;;width:170px;white-space:nowrap;vertical-align:top">MERaLiON-3-3B-ASR</td>
|
| 212 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">我是哪的 recruit 啊按怎没有 helmet 我是 recruit 咩有 full pack 按怎你没有 full pack 我有啊我今天就是 full pack。</td>
|
| 213 |
+
</tr>
|
| 214 |
+
<tr>
|
| 215 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#888;;width:170px;white-space:nowrap;vertical-align:top">gemini-3.5-flash</td>
|
| 216 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">Oh my god, 我是那一個 record。安仔，無 feedback 係點呀？Oh my god, 乜嘢 feedback 呀？我係，我係 record 嗰個。人哋有 feedback，你點解無 feedback 呀？Oh my god, 我呢個就係 feedback。</td>
|
| 217 |
+
</tr>
|
| 218 |
+
</tbody></table>
|
| 219 |
+
<h4 style="margin:18px 0 6px 0;color:#1e6f8b">Code-switching (Tamil + English)</h4>
|
| 220 |
+
<audio controls preload="none" src="https://huggingface.co/MERaLiON/MERaLiON-3-3B-ASR/resolve/main/assets/samples/3_codeswitch_tamil.wav" style="width:100%;max-width:520px"></audio>
|
| 221 |
+
<table style="width:100%;border-collapse:collapse;font-size:13px;margin:6px 0 4px 0">
|
| 222 |
+
<tbody>
|
| 223 |
+
<tr>
|
| 224 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#444;font-weight:600;width:170px;white-space:nowrap">Reference</td>
|
| 225 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">நாம்ம என்ன snacks வீட்ல சைரோ எல்லா snacks கூட குடுக்கலாம்</td>
|
| 226 |
+
</tr>
|
| 227 |
+
<tr>
|
| 228 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;;width:170px;white-space:nowrap">MERaLiON-3-ASR-API</td>
|
| 229 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">நம்ம என்ன snacks வீட்ல சேரு எல்லா snacks கூட கொடுக்கலாம்.</td>
|
| 230 |
+
</tr>
|
| 231 |
+
<tr>
|
| 232 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#444;;width:170px;white-space:nowrap">MERaLiON-3-3B-ASR</td>
|
| 233 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">நம்ம என்ன snacks வீட்ல சேர்ற எல்லா snacks கூட குடுக்கலாம்.</td>
|
| 234 |
+
</tr>
|
| 235 |
+
<tr>
|
| 236 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#888;;width:170px;white-space:nowrap">gemini-3.5-flash</td>
|
| 237 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">நம்ம என்ன ஸ்நாக்ஸ் வீட்டுல செய்யற எல்லா ஸ்நாக்ஸ் கூட கொடுக்கலாம்</td>
|
| 238 |
+
</tr>
|
| 239 |
+
</tbody></table>
|
| 240 |
+
<h4 style="margin:18px 0 6px 0;color:#1e6f8b">Code-switching (English + Mandarin)</h4>
|
| 241 |
+
<audio controls preload="none" src="https://huggingface.co/MERaLiON/MERaLiON-3-3B-ASR/resolve/main/assets/samples/4_codeswitch_singlish.wav" style="width:100%;max-width:520px"></audio>
|
| 242 |
+
<table style="width:100%;border-collapse:collapse;font-size:13px;margin:6px 0 4px 0">
|
| 243 |
+
<tbody>
|
| 244 |
+
<tr>
|
| 245 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#444;font-weight:600;width:170px;white-space:nowrap">Reference</td>
|
| 246 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">there's like two quarters 嘛 then 他 会 教</td>
|
| 247 |
+
</tr>
|
| 248 |
+
<tr>
|
| 249 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#1e6f8b;;width:170px;white-space:nowrap">MERaLiON-3-ASR-API</td>
|
| 250 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">there's like two quarters (mah) then 他会教。</td>
|
| 251 |
+
</tr>
|
| 252 |
+
<tr>
|
| 253 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#444;;width:170px;white-space:nowrap">MERaLiON-3-3B-ASR</td>
|
| 254 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">there's like two quarters (mah) then 他会叫。</td>
|
| 255 |
+
</tr>
|
| 256 |
+
<tr>
|
| 257 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);color:#888;;width:170px;white-space:nowrap">gemini-3.5-flash</td>
|
| 258 |
+
<td style="padding:4px 10px;border-bottom:1px solid rgba(128, 128, 128, 0.15);font-family:monospace">that's like two quarters then how would you</td>
|
| 259 |
+
</tr>
|
| 260 |
+
</tbody></table>
|
| 261 |
+
</div>
|
| 262 |
+
|
| 263 |
+
## A note on the code-switching benchmark
|
| 264 |
+
|
| 265 |
+
The code-switching section aggregates 13 datasets of natural Southeast Asian conversational speech, totalling 5,430 samples / 35.4 hours, in which English is mixed organically with another SEA language. Coverage by direction:
|
| 266 |
+
|
| 267 |
+
| Code-switch direction | Samples | Hours |
|
| 268 |
+
|---|---:|---:|
|
| 269 |
+
| EN ↔ Mandarin (incl. SEAME) | 506 | 5.3 |
|
| 270 |
+
| IMDA Part 4 (Singlish, EN ↔ Mandarin) | 1,000 | 7.3 |
|
| 271 |
+
| EN ↔ Tamil | 2,184 | 9.0 |
|
| 272 |
+
| EN ↔ Cantonese | 904 | 6.2 |
|
| 273 |
+
| EN ↔ Hokkien | 536 | 3.7 |
|
| 274 |
+
| EN ↔ Malay | 200 | 2.6 |
|
| 275 |
+
| EN ↔ Vietnamese | 100 | 1.3 |
|
| 276 |
+
|
| 277 |
+
The benchmark is intended to capture real-world SEA usage patterns rather than synthetic alternation between scripts. Of the constituent corpora, only [IMDA Part 4 (NSC)](https://www.imda.gov.sg/how-we-can-help/national-speech-corpus) is publicly available; the remaining datasets are proprietary or curated in-house. Per-sample normalisation and scoring scripts for the whole evaluation are available at [SEA-SpeechBench](https://github.com/SEA-SpeechBench/SEA-SpeechBench).
|
| 278 |
+
|
| 279 |
+
## Model Description
|
| 280 |
+
|
| 281 |
+
| Property | Value |
|
| 282 |
+
|----------|-------|
|
| 283 |
+
| Audio format | Mono, 16,000 Hz |
|
| 284 |
+
| Parameters | 3 B |
|
| 285 |
+
| Precision | BF16 |
|
| 286 |
+
| Supported languages | English (Global + Singapore), Mandarin, Malay, Tamil, Indonesian, Thai, Vietnamese, Cantonese, Hokkien |
|
| 287 |
+
| Supported backend | vLLM |
|
| 288 |
+
|
| 289 |
+
The model is trained as an ASR-optimised fine-tune over a multilingual mixture of curated Southeast Asian speech data, with particular emphasis on Singapore English, regional dialects (Cantonese, Hokkien), and natural English-X code-switching.
|
| 290 |
+
|
| 291 |
+
## How to Use
|
| 292 |
+
|
| 293 |
+
The recommended way to run MERaLiON-3-3B-ASR is through the [`meralion-3-asr`](https://github.com/YingxuH/MERaLiON-3-ASR) Python package, which wraps a vLLM backend tuned for this model. Install directly from source:
|
| 294 |
+
|
| 295 |
+
```bash
|
| 296 |
+
pip install "meralion-3-asr[vllm] @ git+https://github.com/YingxuH/MERaLiON-3-ASR.git"
|
| 297 |
+
```
|
| 298 |
+
|
| 299 |
+
The package pre-wires the transcription prompt, decoding configuration, no-repeat-ngram guard, and 30 s audio chunking — on both the offline path and the served path. Callers only provide audio.
|
| 300 |
+
|
| 301 |
+
### 1. Offline batch (in-process vLLM)
|
| 302 |
+
|
| 303 |
+
```python
|
| 304 |
+
from meralion_3_asr import Meralion3ASR
|
| 305 |
+
|
| 306 |
+
model = Meralion3ASR.from_pretrained("MERaLiON/MERaLiON-3-3B-ASR", backend="vllm")
|
| 307 |
+
|
| 308 |
+
text = model.transcribe("audio.wav") # str
|
| 309 |
+
texts = model.transcribe_batch(["a.wav", "b.wav", "c.wav"]) # List[str]
|
| 310 |
+
```
|
| 311 |
+
|
| 312 |
+
Inputs may be local file paths, `https://` URLs, base64 data URLs, or `(numpy_array, sample_rate)` tuples. Audio is automatically resampled to mono 16 kHz; long files are chunked transparently.
|
| 313 |
+
|
| 314 |
+
### 2. Serving via the bundled sidecar
|
| 315 |
+
|
| 316 |
+
`meralion-3-asr serve` starts a FastAPI sidecar fronting an internal `vllm serve` process. The sidecar exposes a single OpenAI-compatible endpoint, `/v1/audio/transcriptions`, applies 30 s non-overlapping chunking server-side, and forwards each chunk to the internal vLLM. Clients send audio only — no prompt, no decoding flags.
|
| 317 |
+
|
| 318 |
+
```bash
|
| 319 |
+
meralion-3-asr serve --model MERaLiON/MERaLiON-3-3B-ASR --port 8000
|
| 320 |
+
```
|
| 321 |
+
|
| 322 |
+
OpenAI Python SDK:
|
| 323 |
+
|
| 324 |
+
```python
|
| 325 |
+
from openai import OpenAI
|
| 326 |
+
|
| 327 |
+
client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
|
| 328 |
+
|
| 329 |
+
with open("audio.wav", "rb") as f:
|
| 330 |
+
resp = client.audio.transcriptions.create(
|
| 331 |
+
model="MERaLiON/MERaLiON-3-3B-ASR",
|
| 332 |
+
file=f,
|
| 333 |
+
)
|
| 334 |
+
print(resp.text)
|
| 335 |
+
```
|
| 336 |
+
|
| 337 |
+
curl:
|
| 338 |
+
|
| 339 |
+
```bash
|
| 340 |
+
curl -s -X POST http://localhost:8000/v1/audio/transcriptions \
|
| 341 |
+
-F "model=MERaLiON/MERaLiON-3-3B-ASR" \
|
| 342 |
+
-F "file=@audio.wav" \
|
| 343 |
+
| jq -r .text
|
| 344 |
+
```
|
| 345 |
+
|
| 346 |
+
A `transformers` backend is also available for debugging and small-scale use, but is currently considered experimental — the vLLM backend is the only fully supported and benchmarked path.
|
| 347 |
+
|
| 348 |
+
## Hardware & Infrastructure
|
| 349 |
+
|
| 350 |
+
MERaLiON-3 was trained on the **ASPIRE 2A+** supercomputer cluster at the National Supercomputing Centre (NSCC), Singapore, hosted by A\*STAR I2R:
|
| 351 |
+
|
| 352 |
+
- **GPUs**: 128 Nvidia H100 GPUs (16 nodes × 8 H100)
|
| 353 |
+
- **Memory**: 2 TB RAM per node
|
| 354 |
+
- **Storage**: 30 TB NVMe per node + 2.5 PB SSD-based Lustre filesystem
|
| 355 |
+
- **Interconnect**: 400 Gb/s NDR InfiniBand (full fat-tree topology)
|
| 356 |
+
|
| 357 |
+
## Related Resources
|
| 358 |
+
|
| 359 |
+
- [meralion-3-asr Python package (GitHub)](https://github.com/YingxuH/MERaLiON-3-ASR)
|
| 360 |
+
- [SEA-SpeechBench evaluation harness](https://github.com/SEA-SpeechBench/SEA-SpeechBench)
|
| 361 |
+
- Related models:
|
| 362 |
+
- [MERaLiON-2-10B-ASR](https://huggingface.co/MERaLiON/MERaLiON-2-10B-ASR)
|
| 363 |
+
- [MERaLiON-2-3B](https://huggingface.co/MERaLiON/MERaLiON-2-3B)
|
| 364 |
+
- [MERaLiON-2-10B](https://huggingface.co/MERaLiON/MERaLiON-2-10B)
|
| 365 |
+
|
| 366 |
+
## License
|
| 367 |
+
|
| 368 |
+
License: TBD.
|
| 369 |
+
|
| 370 |
+
## Disclaimer
|
| 371 |
+
|
| 372 |
+
⚠️ MERaLiON-3-3B-ASR has not been specifically aligned for safety and may transcribe content that is inappropriate, offensive, or harmful. Developers and users are responsible for performing their own safety fine-tuning and implementing necessary security measures. The authors shall not be held liable for any claims, damages, or other liabilities arising from the use of the released models, weights, or code.
|
| 373 |
+
|
| 374 |
+
## Citation
|
| 375 |
+
|
| 376 |
+
If you use MERaLiON-3-3B-ASR in your work, please cite the foundational MERaLiON references:
|
| 377 |
+
|
| 378 |
+
```bibtex
|
| 379 |
+
@misc{he2024meralionaudiollmtechnicalreport,
|
| 380 |
+
title={MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models},
|
| 381 |
+
author={{MERaLiON Team}},
|
| 382 |
+
year={2024},
|
| 383 |
+
eprint={2412.09818},
|
| 384 |
+
archivePrefix={arXiv},
|
| 385 |
+
primaryClass={cs.CL},
|
| 386 |
+
url={https://arxiv.org/abs/2412.09818},
|
| 387 |
+
}
|
| 388 |
+
|
| 389 |
+
@article{wang2024audiobench,
|
| 390 |
+
title={AudioBench: A Universal Benchmark for Audio Large Language Models},
|
| 391 |
+
author={Wang, Bin and Zou, Xunlong and Lin, Geyu and Sun, Shuo and Liu, Zhuohan and Zhang, Wenyu and Liu, Zhengyuan and Aw, AiTi and Chen, Nancy F},
|
| 392 |
+
journal={NAACL},
|
| 393 |
+
year={2025}
|
| 394 |
+
}
|
| 395 |
+
|
| 396 |
+
@article{wang2025advancing,
|
| 397 |
+
title={Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models},
|
| 398 |
+
author={Wang, Bin and Zou, Xunlong and Sun, Shuo and Zhang, Wenyu and He, Yingxu and Liu, Zhuohan and Wei, Chengwei and Chen, Nancy F and Aw, AiTi},
|
| 399 |
+
journal={arXiv preprint arXiv:2501.01034},
|
| 400 |
+
year={2025}
|
| 401 |
+
}
|
| 402 |
+
|
| 403 |
+
@article{zhang2024mowe,
|
| 404 |
+
title={MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders},
|
| 405 |
+
author={Zhang, Wenyu and Sun, Shuo and Wang, Bin and Zou, Xunlong and Liu, Zhuohan and He, Yingxu and Lin, Geyu and Chen, Nancy F and Aw, Ai Ti},
|
| 406 |
+
journal={ICASSP},
|
| 407 |
+
year={2025}
|
| 408 |
+
}
|
| 409 |
+
```
|
assets/meralion_hf_comparison.png
ADDED
|
Git LFS Details
|
assets/samples/1_cantonese.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4165f9fcd06802ca0865c33e815161f2a28d45b7bcd93a53f5a5bfaa656f9f58
|
| 3 |
+
size 288044
|
assets/samples/2_hokkien.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a683835a420a13467165d8b8e818bb0fce0ae2d6f5f31e1ef520ed0df49f3479
|
| 3 |
+
size 566444
|
assets/samples/3_codeswitch_tamil.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c419ea7957fe3e7d73ce41cfac00c530049b52fbc39f5db7b6efc48ee89ae09
|
| 3 |
+
size 115596
|
assets/samples/4_codeswitch_singlish.wav
ADDED
|
Binary file (78.4 kB). View file
|
|
|
config.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MERaLiON3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration_meralion3.MERaLiON3Config",
|
| 7 |
+
"AutoModelForSpeechSeq2Seq": "modeling_meralion3.MERaLiON3ForConditionalGeneration"
|
| 8 |
+
},
|
| 9 |
+
"fixed_speech_embeds_length": 300,
|
| 10 |
+
"head_dim": 256,
|
| 11 |
+
"hidden_size": 2304,
|
| 12 |
+
"intermediate_size": 9216,
|
| 13 |
+
"model_type": "meralion3",
|
| 14 |
+
"num_attention_heads": 8,
|
| 15 |
+
"num_hidden_layers": 26,
|
| 16 |
+
"num_key_value_heads": 4,
|
| 17 |
+
"sliding_window": 4096,
|
| 18 |
+
"speech_config": {
|
| 19 |
+
"_attn_implementation_autoset": true,
|
| 20 |
+
"_name_or_path": "/data/projects/13003558/sunshuo/models/meralion_whisper_v3_normed_cleaned",
|
| 21 |
+
"activation_dropout": 0.0,
|
| 22 |
+
"activation_function": "gelu",
|
| 23 |
+
"apply_spec_augment": true,
|
| 24 |
+
"architectures": [
|
| 25 |
+
"WhisperForConditionalGeneration"
|
| 26 |
+
],
|
| 27 |
+
"attention_dropout": 0.0,
|
| 28 |
+
"begin_suppress_tokens": null,
|
| 29 |
+
"bos_token_id": 50257,
|
| 30 |
+
"classifier_proj_size": 256,
|
| 31 |
+
"d_model": 1280,
|
| 32 |
+
"decoder_attention_heads": 20,
|
| 33 |
+
"decoder_ffn_dim": 5120,
|
| 34 |
+
"decoder_layerdrop": 0.0,
|
| 35 |
+
"decoder_layers": 32,
|
| 36 |
+
"decoder_start_token_id": 50258,
|
| 37 |
+
"dropout": 0.0,
|
| 38 |
+
"encoder_attention_heads": 20,
|
| 39 |
+
"encoder_ffn_dim": 5120,
|
| 40 |
+
"encoder_layerdrop": 0.0,
|
| 41 |
+
"encoder_layers": 32,
|
| 42 |
+
"eos_token_id": 50257,
|
| 43 |
+
"init_std": 0.02,
|
| 44 |
+
"mask_feature_length": 10,
|
| 45 |
+
"mask_feature_min_masks": 0,
|
| 46 |
+
"mask_feature_prob": 0.1,
|
| 47 |
+
"mask_time_length": 20,
|
| 48 |
+
"mask_time_min_masks": 2,
|
| 49 |
+
"mask_time_prob": 0.1,
|
| 50 |
+
"max_length": null,
|
| 51 |
+
"max_source_positions": 1500,
|
| 52 |
+
"max_target_positions": 448,
|
| 53 |
+
"median_filter_width": 7,
|
| 54 |
+
"model_type": "whisper",
|
| 55 |
+
"num_hidden_layers": 32,
|
| 56 |
+
"num_mel_bins": 128,
|
| 57 |
+
"scale_embedding": false,
|
| 58 |
+
"torch_dtype": "bfloat16",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"use_weighted_layer_sum": false,
|
| 61 |
+
"vocab_size": 51866
|
| 62 |
+
},
|
| 63 |
+
"speech_mlp_scale_factor": 5,
|
| 64 |
+
"speech_mlp_use_projection": false,
|
| 65 |
+
"speech_token_index": 255999,
|
| 66 |
+
"text_config": {
|
| 67 |
+
"_attn_implementation_autoset": true,
|
| 68 |
+
"_name_or_path": "google/gemma-2-2b-it",
|
| 69 |
+
"architectures": [
|
| 70 |
+
"Gemma2ForCausalLM"
|
| 71 |
+
],
|
| 72 |
+
"attention_bias": false,
|
| 73 |
+
"attention_dropout": 0.0,
|
| 74 |
+
"attn_logit_softcapping": 50.0,
|
| 75 |
+
"cache_implementation": "hybrid",
|
| 76 |
+
"final_logit_softcapping": 30.0,
|
| 77 |
+
"head_dim": 256,
|
| 78 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 79 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 80 |
+
"hidden_size": 2304,
|
| 81 |
+
"initializer_range": 0.02,
|
| 82 |
+
"intermediate_size": 9216,
|
| 83 |
+
"max_position_embeddings": 8192,
|
| 84 |
+
"model_type": "gemma2",
|
| 85 |
+
"num_attention_heads": 8,
|
| 86 |
+
"num_hidden_layers": 26,
|
| 87 |
+
"num_key_value_heads": 4,
|
| 88 |
+
"query_pre_attn_scalar": 256,
|
| 89 |
+
"rms_norm_eps": 1e-06,
|
| 90 |
+
"rope_theta": 10000.0,
|
| 91 |
+
"sliding_window": 4096,
|
| 92 |
+
"torch_dtype": "bfloat16",
|
| 93 |
+
"use_cache": true,
|
| 94 |
+
"vocab_size": 256000
|
| 95 |
+
},
|
| 96 |
+
"torch_dtype": "bfloat16",
|
| 97 |
+
"transformers_version": "4.50.1"
|
| 98 |
+
}
|
configuration_meralion3.py
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""MERaLiON3 model configuration"""
|
| 2 |
+
|
| 3 |
+
from transformers import Gemma2Config, WhisperConfig
|
| 4 |
+
from transformers.configuration_utils import PretrainedConfig
|
| 5 |
+
from transformers.utils import logging
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
logger = logging.get_logger(__name__)
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
class MERaLiON3Config(PretrainedConfig):
|
| 12 |
+
r"""
|
| 13 |
+
This is the configuration class to store the configuration of a [`MERaLiON3ForConditionalGeneration`]. It is used to instantiate an
|
| 14 |
+
MERaLiON3 model according to the specified arguments, defining the model architecture. Instantiating a configuration
|
| 15 |
+
with the defaults will yield a similar configuration to that of the MERaLiON3.
|
| 16 |
+
|
| 17 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
| 18 |
+
documentation from [`PretrainedConfig`] for more information.
|
| 19 |
+
|
| 20 |
+
Args:
|
| 21 |
+
audio_config (`Union[AutoConfig, dict]`, *optional*, defaults to `CLIPVisionConfig`):
|
| 22 |
+
The config object or dictionary of the audio backbone.
|
| 23 |
+
text_config (`Union[AutoConfig, dict]`, *optional*, defaults to `LlamaConfig`):
|
| 24 |
+
The config object or dictionary of the text backbone.
|
| 25 |
+
audio_token_index (`int`, *optional*, defaults to 151646):
|
| 26 |
+
The image token index to encode the image prompt.
|
| 27 |
+
"""
|
| 28 |
+
|
| 29 |
+
model_type = "meralion3"
|
| 30 |
+
is_composition = False
|
| 31 |
+
|
| 32 |
+
def __init__(
|
| 33 |
+
self,
|
| 34 |
+
speech_config=None,
|
| 35 |
+
text_config=None,
|
| 36 |
+
speech_mlp_use_projection=True,
|
| 37 |
+
speech_mlp_scale_factor=15,
|
| 38 |
+
speech_token_index=255999,
|
| 39 |
+
fixed_speech_embeds_length=100,
|
| 40 |
+
**kwargs,
|
| 41 |
+
):
|
| 42 |
+
|
| 43 |
+
if isinstance(speech_config, dict):
|
| 44 |
+
speech_config = WhisperConfig(**speech_config)
|
| 45 |
+
elif speech_config is None:
|
| 46 |
+
speech_config = WhisperConfig(
|
| 47 |
+
d_model=1280,
|
| 48 |
+
encoder_attention_heads=20,
|
| 49 |
+
encoder_ffn_dim=5120,
|
| 50 |
+
encoder_layerdrop=0.0,
|
| 51 |
+
encoder_layers=32,
|
| 52 |
+
num_mel_bins=128,
|
| 53 |
+
max_source_positions=1500,
|
| 54 |
+
scale_embedding=False,
|
| 55 |
+
activation_function="gelu",
|
| 56 |
+
)
|
| 57 |
+
|
| 58 |
+
self.speech_config = speech_config
|
| 59 |
+
|
| 60 |
+
if isinstance(text_config, dict):
|
| 61 |
+
text_config = Gemma2Config(**text_config)
|
| 62 |
+
elif text_config is None:
|
| 63 |
+
text_config = Gemma2Config()
|
| 64 |
+
|
| 65 |
+
self.text_config = text_config
|
| 66 |
+
|
| 67 |
+
self.speech_mlp_use_projection = speech_mlp_use_projection
|
| 68 |
+
self.speech_mlp_scale_factor = speech_mlp_scale_factor
|
| 69 |
+
self.speech_token_index = speech_token_index
|
| 70 |
+
self.fixed_speech_embeds_length = fixed_speech_embeds_length
|
| 71 |
+
|
| 72 |
+
self.sliding_window = self.text_config.sliding_window
|
| 73 |
+
self.hidden_size = self.text_config.hidden_size
|
| 74 |
+
self.num_attention_heads = self.text_config.num_attention_heads
|
| 75 |
+
self.num_hidden_layers = self.text_config.num_hidden_layers
|
| 76 |
+
self.num_key_value_heads = self.text_config.num_key_value_heads
|
| 77 |
+
self.head_dim = self.text_config.head_dim
|
| 78 |
+
self.intermediate_size = self.text_config.intermediate_size
|
| 79 |
+
|
| 80 |
+
super().__init__(**kwargs)
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"cache_implementation": "hybrid",
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"no_repeat_ngram_size": 6,
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"repetition_penalty": 1.05,
|
| 9 |
+
"transformers_version": "4.50.1"
|
| 10 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea836de00d15a94685d9b69189d0073c9248aa264790634cda38d2cf9b26baac
|
| 3 |
+
size 4971858576
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c1472c987cf7360c628c7da8881ff1aad6a7fa00d42de3d07424c0862b7804f
|
| 3 |
+
size 1642292496
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,788 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 6614055424
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"ln_speech.bias": "model-00001-of-00002.safetensors",
|
| 7 |
+
"ln_speech.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"speech_audio_adapter.mlp_adapter.0.bias": "model-00001-of-00002.safetensors",
|
| 9 |
+
"speech_audio_adapter.mlp_adapter.0.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"speech_audio_adapter.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 11 |
+
"speech_audio_adapter.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"speech_encoder.conv1.bias": "model-00001-of-00002.safetensors",
|
| 13 |
+
"speech_encoder.conv1.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"speech_encoder.conv2.bias": "model-00001-of-00002.safetensors",
|
| 15 |
+
"speech_encoder.conv2.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"speech_encoder.embed_positions.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"speech_encoder.layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"speech_encoder.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"speech_encoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
|
| 20 |
+
"speech_encoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"speech_encoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
|
| 22 |
+
"speech_encoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"speech_encoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 24 |
+
"speech_encoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"speech_encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"speech_encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 27 |
+
"speech_encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"speech_encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"speech_encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"speech_encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"speech_encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"speech_encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 33 |
+
"speech_encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"speech_encoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
|
| 35 |
+
"speech_encoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"speech_encoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
|
| 37 |
+
"speech_encoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"speech_encoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 39 |
+
"speech_encoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"speech_encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"speech_encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"speech_encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"speech_encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 44 |
+
"speech_encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"speech_encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 46 |
+
"speech_encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"speech_encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 48 |
+
"speech_encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"speech_encoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"speech_encoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"speech_encoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
|
| 52 |
+
"speech_encoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"speech_encoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"speech_encoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"speech_encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"speech_encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 57 |
+
"speech_encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"speech_encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 59 |
+
"speech_encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"speech_encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 61 |
+
"speech_encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"speech_encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 63 |
+
"speech_encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"speech_encoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"speech_encoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"speech_encoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"speech_encoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"speech_encoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 69 |
+
"speech_encoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"speech_encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"speech_encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 72 |
+
"speech_encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"speech_encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"speech_encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"speech_encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 76 |
+
"speech_encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"speech_encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"speech_encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"speech_encoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
|
| 80 |
+
"speech_encoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"speech_encoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
|
| 82 |
+
"speech_encoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"speech_encoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 84 |
+
"speech_encoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"speech_encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"speech_encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 87 |
+
"speech_encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"speech_encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"speech_encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"speech_encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 91 |
+
"speech_encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"speech_encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 93 |
+
"speech_encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"speech_encoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
|
| 95 |
+
"speech_encoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"speech_encoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
|
| 97 |
+
"speech_encoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"speech_encoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 99 |
+
"speech_encoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"speech_encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"speech_encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"speech_encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"speech_encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 104 |
+
"speech_encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"speech_encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 106 |
+
"speech_encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"speech_encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 108 |
+
"speech_encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"speech_encoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"speech_encoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"speech_encoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
|
| 112 |
+
"speech_encoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"speech_encoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"speech_encoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"speech_encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"speech_encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 117 |
+
"speech_encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"speech_encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 119 |
+
"speech_encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"speech_encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 121 |
+
"speech_encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"speech_encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 123 |
+
"speech_encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"speech_encoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"speech_encoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"speech_encoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"speech_encoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"speech_encoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 129 |
+
"speech_encoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"speech_encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"speech_encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 132 |
+
"speech_encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"speech_encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"speech_encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"speech_encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 136 |
+
"speech_encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"speech_encoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 138 |
+
"speech_encoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"speech_encoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
|
| 140 |
+
"speech_encoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"speech_encoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
|
| 142 |
+
"speech_encoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"speech_encoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 144 |
+
"speech_encoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"speech_encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"speech_encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 147 |
+
"speech_encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"speech_encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"speech_encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"speech_encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"speech_encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"speech_encoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 153 |
+
"speech_encoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"speech_encoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
|
| 155 |
+
"speech_encoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"speech_encoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
|
| 157 |
+
"speech_encoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"speech_encoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 159 |
+
"speech_encoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"speech_encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"speech_encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"speech_encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"speech_encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 164 |
+
"speech_encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"speech_encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 166 |
+
"speech_encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"speech_encoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 168 |
+
"speech_encoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"speech_encoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"speech_encoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"speech_encoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
|
| 172 |
+
"speech_encoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"speech_encoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 174 |
+
"speech_encoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"speech_encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"speech_encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 177 |
+
"speech_encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"speech_encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 179 |
+
"speech_encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"speech_encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 181 |
+
"speech_encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"speech_encoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 183 |
+
"speech_encoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"speech_encoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
|
| 185 |
+
"speech_encoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"speech_encoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"speech_encoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"speech_encoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 189 |
+
"speech_encoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"speech_encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"speech_encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 192 |
+
"speech_encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"speech_encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 194 |
+
"speech_encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"speech_encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 196 |
+
"speech_encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"speech_encoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 198 |
+
"speech_encoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"speech_encoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
|
| 200 |
+
"speech_encoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"speech_encoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
|
| 202 |
+
"speech_encoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"speech_encoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 204 |
+
"speech_encoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"speech_encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"speech_encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 207 |
+
"speech_encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"speech_encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 209 |
+
"speech_encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"speech_encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 211 |
+
"speech_encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"speech_encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 213 |
+
"speech_encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"speech_encoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
|
| 215 |
+
"speech_encoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"speech_encoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
|
| 217 |
+
"speech_encoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"speech_encoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 219 |
+
"speech_encoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"speech_encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"speech_encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 222 |
+
"speech_encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"speech_encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 224 |
+
"speech_encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"speech_encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 226 |
+
"speech_encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"speech_encoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 228 |
+
"speech_encoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"speech_encoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
|
| 230 |
+
"speech_encoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"speech_encoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
|
| 232 |
+
"speech_encoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"speech_encoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 234 |
+
"speech_encoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"speech_encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"speech_encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 237 |
+
"speech_encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"speech_encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 239 |
+
"speech_encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"speech_encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 241 |
+
"speech_encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"speech_encoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 243 |
+
"speech_encoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"speech_encoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
|
| 245 |
+
"speech_encoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"speech_encoder.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
|
| 247 |
+
"speech_encoder.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"speech_encoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 249 |
+
"speech_encoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"speech_encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"speech_encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 252 |
+
"speech_encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"speech_encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 254 |
+
"speech_encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"speech_encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 256 |
+
"speech_encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"speech_encoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"speech_encoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"speech_encoder.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"speech_encoder.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"speech_encoder.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
|
| 262 |
+
"speech_encoder.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"speech_encoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 264 |
+
"speech_encoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"speech_encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"speech_encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 267 |
+
"speech_encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"speech_encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"speech_encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"speech_encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"speech_encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"speech_encoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 273 |
+
"speech_encoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"speech_encoder.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
|
| 275 |
+
"speech_encoder.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"speech_encoder.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
|
| 277 |
+
"speech_encoder.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"speech_encoder.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 279 |
+
"speech_encoder.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"speech_encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"speech_encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"speech_encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"speech_encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"speech_encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"speech_encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 286 |
+
"speech_encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"speech_encoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 288 |
+
"speech_encoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"speech_encoder.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"speech_encoder.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"speech_encoder.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
|
| 292 |
+
"speech_encoder.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"speech_encoder.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"speech_encoder.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"speech_encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"speech_encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 297 |
+
"speech_encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"speech_encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 299 |
+
"speech_encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"speech_encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 301 |
+
"speech_encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"speech_encoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 303 |
+
"speech_encoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"speech_encoder.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"speech_encoder.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"speech_encoder.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"speech_encoder.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"speech_encoder.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 309 |
+
"speech_encoder.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"speech_encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"speech_encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 312 |
+
"speech_encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"speech_encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"speech_encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"speech_encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 316 |
+
"speech_encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"speech_encoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"speech_encoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"speech_encoder.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
|
| 320 |
+
"speech_encoder.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"speech_encoder.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
|
| 322 |
+
"speech_encoder.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"speech_encoder.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 324 |
+
"speech_encoder.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"speech_encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"speech_encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 327 |
+
"speech_encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"speech_encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"speech_encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"speech_encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"speech_encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"speech_encoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 333 |
+
"speech_encoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"speech_encoder.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
|
| 335 |
+
"speech_encoder.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"speech_encoder.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
|
| 337 |
+
"speech_encoder.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"speech_encoder.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 339 |
+
"speech_encoder.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"speech_encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"speech_encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 342 |
+
"speech_encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"speech_encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"speech_encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"speech_encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 346 |
+
"speech_encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"speech_encoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 348 |
+
"speech_encoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"speech_encoder.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
|
| 350 |
+
"speech_encoder.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"speech_encoder.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
|
| 352 |
+
"speech_encoder.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"speech_encoder.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 354 |
+
"speech_encoder.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"speech_encoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"speech_encoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 357 |
+
"speech_encoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"speech_encoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 359 |
+
"speech_encoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"speech_encoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 361 |
+
"speech_encoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"speech_encoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 363 |
+
"speech_encoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"speech_encoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
|
| 365 |
+
"speech_encoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"speech_encoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
|
| 367 |
+
"speech_encoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"speech_encoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 369 |
+
"speech_encoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"speech_encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"speech_encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 372 |
+
"speech_encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"speech_encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 374 |
+
"speech_encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"speech_encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 376 |
+
"speech_encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"speech_encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"speech_encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"speech_encoder.layers.30.fc1.bias": "model-00001-of-00002.safetensors",
|
| 380 |
+
"speech_encoder.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"speech_encoder.layers.30.fc2.bias": "model-00001-of-00002.safetensors",
|
| 382 |
+
"speech_encoder.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"speech_encoder.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 384 |
+
"speech_encoder.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"speech_encoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"speech_encoder.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"speech_encoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"speech_encoder.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"speech_encoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"speech_encoder.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"speech_encoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"speech_encoder.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 393 |
+
"speech_encoder.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"speech_encoder.layers.31.fc1.bias": "model-00001-of-00002.safetensors",
|
| 395 |
+
"speech_encoder.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"speech_encoder.layers.31.fc2.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"speech_encoder.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"speech_encoder.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"speech_encoder.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"speech_encoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"speech_encoder.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"speech_encoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"speech_encoder.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 404 |
+
"speech_encoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"speech_encoder.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 406 |
+
"speech_encoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"speech_encoder.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"speech_encoder.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"speech_encoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"speech_encoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"speech_encoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
|
| 412 |
+
"speech_encoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"speech_encoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"speech_encoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"speech_encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"speech_encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 417 |
+
"speech_encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"speech_encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 419 |
+
"speech_encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"speech_encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"speech_encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"speech_encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"speech_encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"speech_encoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"speech_encoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"speech_encoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"speech_encoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"speech_encoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"speech_encoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"speech_encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"speech_encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 432 |
+
"speech_encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"speech_encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"speech_encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"speech_encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 436 |
+
"speech_encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"speech_encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"speech_encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"speech_encoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
|
| 440 |
+
"speech_encoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"speech_encoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"speech_encoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"speech_encoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"speech_encoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"speech_encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"speech_encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"speech_encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"speech_encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"speech_encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"speech_encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"speech_encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"speech_encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"speech_encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"speech_encoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"speech_encoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"speech_encoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"speech_encoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"speech_encoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"speech_encoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"speech_encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"speech_encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 462 |
+
"speech_encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"speech_encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 464 |
+
"speech_encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"speech_encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"speech_encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"speech_encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 468 |
+
"speech_encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"speech_encoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
|
| 470 |
+
"speech_encoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"speech_encoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
|
| 472 |
+
"speech_encoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"speech_encoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 474 |
+
"speech_encoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"speech_encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"speech_encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"speech_encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"speech_encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"speech_encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"speech_encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"speech_encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"speech_encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"speech_encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"speech_encoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"speech_encoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"speech_encoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"speech_encoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"speech_encoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"speech_encoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"speech_encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"speech_encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 492 |
+
"speech_encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"speech_encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 494 |
+
"speech_encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"speech_encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 496 |
+
"speech_encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"speech_encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 498 |
+
"speech_encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"text_decoder.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"text_decoder.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"text_decoder.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"text_decoder.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"text_decoder.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"text_decoder.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"text_decoder.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"text_decoder.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"text_decoder.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"text_decoder.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"text_decoder.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"text_decoder.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"text_decoder.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"text_decoder.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 513 |
+
"text_decoder.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"text_decoder.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"text_decoder.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"text_decoder.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"text_decoder.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"text_decoder.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 519 |
+
"text_decoder.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"text_decoder.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"text_decoder.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"text_decoder.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"text_decoder.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"text_decoder.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"text_decoder.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"text_decoder.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"text_decoder.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"text_decoder.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"text_decoder.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"text_decoder.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"text_decoder.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"text_decoder.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 533 |
+
"text_decoder.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"text_decoder.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"text_decoder.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"text_decoder.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"text_decoder.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"text_decoder.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 539 |
+
"text_decoder.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"text_decoder.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 541 |
+
"text_decoder.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"text_decoder.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"text_decoder.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"text_decoder.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 545 |
+
"text_decoder.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"text_decoder.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"text_decoder.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"text_decoder.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"text_decoder.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"text_decoder.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"text_decoder.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"text_decoder.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"text_decoder.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"text_decoder.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"text_decoder.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"text_decoder.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 557 |
+
"text_decoder.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"text_decoder.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"text_decoder.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"text_decoder.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"text_decoder.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"text_decoder.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"text_decoder.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"text_decoder.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 565 |
+
"text_decoder.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"text_decoder.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"text_decoder.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"text_decoder.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"text_decoder.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"text_decoder.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"text_decoder.model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"text_decoder.model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"text_decoder.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"text_decoder.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"text_decoder.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"text_decoder.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"text_decoder.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"text_decoder.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 579 |
+
"text_decoder.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"text_decoder.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 581 |
+
"text_decoder.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"text_decoder.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"text_decoder.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"text_decoder.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"text_decoder.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"text_decoder.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 587 |
+
"text_decoder.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"text_decoder.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"text_decoder.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"text_decoder.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 591 |
+
"text_decoder.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"text_decoder.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"text_decoder.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"text_decoder.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 595 |
+
"text_decoder.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"text_decoder.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 597 |
+
"text_decoder.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"text_decoder.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 599 |
+
"text_decoder.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"text_decoder.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 601 |
+
"text_decoder.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"text_decoder.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 603 |
+
"text_decoder.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"text_decoder.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 605 |
+
"text_decoder.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"text_decoder.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 607 |
+
"text_decoder.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"text_decoder.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 609 |
+
"text_decoder.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"text_decoder.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 611 |
+
"text_decoder.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 612 |
+
"text_decoder.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 613 |
+
"text_decoder.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 614 |
+
"text_decoder.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 615 |
+
"text_decoder.model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 616 |
+
"text_decoder.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 617 |
+
"text_decoder.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 618 |
+
"text_decoder.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 619 |
+
"text_decoder.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"text_decoder.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 621 |
+
"text_decoder.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 622 |
+
"text_decoder.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"text_decoder.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 624 |
+
"text_decoder.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 625 |
+
"text_decoder.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 626 |
+
"text_decoder.model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"text_decoder.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 628 |
+
"text_decoder.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"text_decoder.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"text_decoder.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 631 |
+
"text_decoder.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"text_decoder.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"text_decoder.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"text_decoder.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"text_decoder.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"text_decoder.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 637 |
+
"text_decoder.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"text_decoder.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"text_decoder.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"text_decoder.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"text_decoder.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"text_decoder.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"text_decoder.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"text_decoder.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 645 |
+
"text_decoder.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"text_decoder.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"text_decoder.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"text_decoder.model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 649 |
+
"text_decoder.model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"text_decoder.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 651 |
+
"text_decoder.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"text_decoder.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 653 |
+
"text_decoder.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"text_decoder.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 655 |
+
"text_decoder.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"text_decoder.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 657 |
+
"text_decoder.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"text_decoder.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 659 |
+
"text_decoder.model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"text_decoder.model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"text_decoder.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"text_decoder.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 663 |
+
"text_decoder.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"text_decoder.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 665 |
+
"text_decoder.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"text_decoder.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 667 |
+
"text_decoder.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"text_decoder.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 669 |
+
"text_decoder.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"text_decoder.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 671 |
+
"text_decoder.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"text_decoder.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 673 |
+
"text_decoder.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"text_decoder.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 675 |
+
"text_decoder.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"text_decoder.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 677 |
+
"text_decoder.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"text_decoder.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 679 |
+
"text_decoder.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"text_decoder.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 681 |
+
"text_decoder.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"text_decoder.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 683 |
+
"text_decoder.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"text_decoder.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"text_decoder.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"text_decoder.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 687 |
+
"text_decoder.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"text_decoder.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 689 |
+
"text_decoder.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"text_decoder.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 691 |
+
"text_decoder.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"text_decoder.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 693 |
+
"text_decoder.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"text_decoder.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 695 |
+
"text_decoder.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"text_decoder.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 697 |
+
"text_decoder.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"text_decoder.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 699 |
+
"text_decoder.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"text_decoder.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 701 |
+
"text_decoder.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"text_decoder.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 703 |
+
"text_decoder.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"text_decoder.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 705 |
+
"text_decoder.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"text_decoder.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 707 |
+
"text_decoder.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"text_decoder.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"text_decoder.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"text_decoder.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 711 |
+
"text_decoder.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"text_decoder.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 713 |
+
"text_decoder.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"text_decoder.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"text_decoder.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"text_decoder.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 717 |
+
"text_decoder.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"text_decoder.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 719 |
+
"text_decoder.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"text_decoder.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 721 |
+
"text_decoder.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"text_decoder.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 723 |
+
"text_decoder.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"text_decoder.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 725 |
+
"text_decoder.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"text_decoder.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 727 |
+
"text_decoder.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"text_decoder.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 729 |
+
"text_decoder.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"text_decoder.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 731 |
+
"text_decoder.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 732 |
+
"text_decoder.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 733 |
+
"text_decoder.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"text_decoder.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 735 |
+
"text_decoder.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"text_decoder.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 737 |
+
"text_decoder.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"text_decoder.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 739 |
+
"text_decoder.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"text_decoder.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 741 |
+
"text_decoder.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 742 |
+
"text_decoder.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 743 |
+
"text_decoder.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"text_decoder.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 745 |
+
"text_decoder.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 746 |
+
"text_decoder.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 747 |
+
"text_decoder.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 748 |
+
"text_decoder.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 749 |
+
"text_decoder.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"text_decoder.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 751 |
+
"text_decoder.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"text_decoder.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 753 |
+
"text_decoder.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"text_decoder.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 755 |
+
"text_decoder.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"text_decoder.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 757 |
+
"text_decoder.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"text_decoder.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 759 |
+
"text_decoder.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"text_decoder.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 761 |
+
"text_decoder.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"text_decoder.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 763 |
+
"text_decoder.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"text_decoder.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 765 |
+
"text_decoder.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"text_decoder.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 767 |
+
"text_decoder.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"text_decoder.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 769 |
+
"text_decoder.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"text_decoder.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 771 |
+
"text_decoder.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 772 |
+
"text_decoder.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 773 |
+
"text_decoder.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"text_decoder.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 775 |
+
"text_decoder.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"text_decoder.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 777 |
+
"text_decoder.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 778 |
+
"text_decoder.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 779 |
+
"text_decoder.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"text_decoder.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 781 |
+
"text_decoder.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 782 |
+
"text_decoder.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 783 |
+
"text_decoder.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 784 |
+
"text_decoder.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 785 |
+
"text_decoder.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"text_decoder.model.norm.weight": "model-00002-of-00002.safetensors"
|
| 787 |
+
}
|
| 788 |
+
}
|
modeling_meralion3.py
ADDED
|
@@ -0,0 +1,567 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""PyTorch MERaLiON3 model."""
|
| 2 |
+
|
| 3 |
+
from dataclasses import dataclass
|
| 4 |
+
from typing import List, Optional, Tuple, Union
|
| 5 |
+
|
| 6 |
+
import torch
|
| 7 |
+
import torch.utils.checkpoint
|
| 8 |
+
from torch import nn
|
| 9 |
+
|
| 10 |
+
from transformers import Gemma2ForCausalLM
|
| 11 |
+
from transformers.models.whisper.modeling_whisper import WhisperEncoder
|
| 12 |
+
from transformers.cache_utils import HybridCache
|
| 13 |
+
from transformers.generation import GenerationMixin
|
| 14 |
+
from transformers.modeling_outputs import ModelOutput
|
| 15 |
+
from transformers.modeling_utils import PreTrainedModel
|
| 16 |
+
from transformers.utils import (
|
| 17 |
+
add_start_docstrings,
|
| 18 |
+
add_start_docstrings_to_model_forward,
|
| 19 |
+
logging,
|
| 20 |
+
replace_return_docstrings,
|
| 21 |
+
)
|
| 22 |
+
|
| 23 |
+
from .configuration_meralion3 import MERaLiON3Config
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
logger = logging.get_logger(__name__)
|
| 27 |
+
|
| 28 |
+
_CONFIG_FOR_DOC = "MERaLiON3Config"
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
# Copied from transformers.models.llama.modeling_llama._prepare_4d_causal_attention_mask_with_cache_position
|
| 32 |
+
def _prepare_4d_causal_attention_mask_with_cache_position(
|
| 33 |
+
attention_mask: torch.Tensor,
|
| 34 |
+
sequence_length: int,
|
| 35 |
+
target_length: int,
|
| 36 |
+
dtype: torch.dtype,
|
| 37 |
+
device: torch.device,
|
| 38 |
+
min_dtype: float,
|
| 39 |
+
cache_position: torch.Tensor,
|
| 40 |
+
batch_size: int,
|
| 41 |
+
):
|
| 42 |
+
"""
|
| 43 |
+
Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape
|
| 44 |
+
`(batch_size, key_value_length)`, or if the input `attention_mask` is already 4D, do nothing.
|
| 45 |
+
|
| 46 |
+
Args:
|
| 47 |
+
attention_mask (`torch.Tensor`):
|
| 48 |
+
A 2D attention mask of shape `(batch_size, key_value_length)` or a 4D attention mask of shape `(batch_size, 1, query_length, key_value_length)`.
|
| 49 |
+
sequence_length (`int`):
|
| 50 |
+
The sequence length being processed.
|
| 51 |
+
target_length (`int`):
|
| 52 |
+
The target length: when generating with static cache, the mask should be as long as the static cache, to account for the 0 padding, the part of the cache that is not filled yet.
|
| 53 |
+
dtype (`torch.dtype`):
|
| 54 |
+
The dtype to use for the 4D attention mask.
|
| 55 |
+
device (`torch.device`):
|
| 56 |
+
The device to plcae the 4D attention mask on.
|
| 57 |
+
min_dtype (`float`):
|
| 58 |
+
The minimum value representable with the dtype `dtype`.
|
| 59 |
+
cache_position (`torch.Tensor`):
|
| 60 |
+
Indices depicting the position of the input sequence tokens in the sequence.
|
| 61 |
+
batch_size (`torch.Tensor`):
|
| 62 |
+
Batch size.
|
| 63 |
+
"""
|
| 64 |
+
if attention_mask is not None and attention_mask.dim() == 4:
|
| 65 |
+
# In this case we assume that the mask comes already in inverted form and requires no inversion or slicing.
|
| 66 |
+
causal_mask = attention_mask
|
| 67 |
+
else:
|
| 68 |
+
causal_mask = torch.full((sequence_length, target_length), fill_value=min_dtype, dtype=dtype, device=device)
|
| 69 |
+
if sequence_length != 1:
|
| 70 |
+
causal_mask = torch.triu(causal_mask, diagonal=1)
|
| 71 |
+
causal_mask *= torch.arange(target_length, device=device) > cache_position.reshape(-1, 1)
|
| 72 |
+
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
|
| 73 |
+
if attention_mask is not None:
|
| 74 |
+
causal_mask = causal_mask.clone() # copy to contiguous memory for in-place edit
|
| 75 |
+
mask_length = attention_mask.shape[-1]
|
| 76 |
+
padding_mask = causal_mask[:, :, :, :mask_length] + attention_mask[:, None, None, :]
|
| 77 |
+
padding_mask = padding_mask == 0
|
| 78 |
+
causal_mask[:, :, :, :mask_length] = causal_mask[:, :, :, :mask_length].masked_fill(
|
| 79 |
+
padding_mask, min_dtype
|
| 80 |
+
)
|
| 81 |
+
return causal_mask
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
# copied from Qwen2AudioCausalLMOutputWithPast
|
| 85 |
+
@dataclass
|
| 86 |
+
class MERaLiON3OutputWithPast(ModelOutput):
|
| 87 |
+
"""
|
| 88 |
+
Base class for MERaLiON3 causal language model (or autoregressive) outputs.
|
| 89 |
+
|
| 90 |
+
Args:
|
| 91 |
+
loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
|
| 92 |
+
Language modeling loss (for next-token prediction).
|
| 93 |
+
logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
|
| 94 |
+
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
|
| 95 |
+
past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
|
| 96 |
+
Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape
|
| 97 |
+
`(batch_size, num_heads, sequence_length, embed_size_per_head)`)
|
| 98 |
+
|
| 99 |
+
Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see
|
| 100 |
+
`past_key_values` input) to speed up sequential decoding.
|
| 101 |
+
hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
|
| 102 |
+
Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
|
| 103 |
+
one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
|
| 104 |
+
|
| 105 |
+
Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
|
| 106 |
+
attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
|
| 107 |
+
Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
|
| 108 |
+
sequence_length)`.
|
| 109 |
+
|
| 110 |
+
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
|
| 111 |
+
heads.
|
| 112 |
+
attention_mask (`torch.FloatTensor`, *optional*):
|
| 113 |
+
Attentions mask, used to update attention mask and position_ids.
|
| 114 |
+
"""
|
| 115 |
+
|
| 116 |
+
loss: Optional[torch.FloatTensor] = None
|
| 117 |
+
logits: torch.FloatTensor = None
|
| 118 |
+
past_key_values: Optional[List[torch.FloatTensor]] = None
|
| 119 |
+
hidden_states: Optional[Tuple[torch.FloatTensor]] = None
|
| 120 |
+
attentions: Optional[Tuple[torch.FloatTensor]] = None
|
| 121 |
+
attention_mask: Optional[torch.FloatTensor] = None
|
| 122 |
+
|
| 123 |
+
|
| 124 |
+
MERALION_START_DOCSTRING = r"""
|
| 125 |
+
This model inherits from [`PreTrainedModel`]. Check the superclass documentation for the generic methods the
|
| 126 |
+
library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads
|
| 127 |
+
etc.)
|
| 128 |
+
|
| 129 |
+
This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass.
|
| 130 |
+
Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage
|
| 131 |
+
and behavior.
|
| 132 |
+
|
| 133 |
+
Parameters:
|
| 134 |
+
config ([`MERaLiON3Config`]):
|
| 135 |
+
Model configuration class with all the parameters of the model. Initializing with a config file does not
|
| 136 |
+
load the weights associated with the model, only the configuration. Check out the
|
| 137 |
+
[`~PreTrainedModel.from_pretrained`] method to load the model weights.
|
| 138 |
+
"""
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
@add_start_docstrings(
|
| 142 |
+
"The bare MERaLiON3 Model outputting raw hidden-states without any specific head on top.",
|
| 143 |
+
MERALION_START_DOCSTRING,
|
| 144 |
+
)
|
| 145 |
+
class MERaLiON3PreTrainedModel(PreTrainedModel):
|
| 146 |
+
config_class = MERaLiON3Config
|
| 147 |
+
base_model_prefix = "model"
|
| 148 |
+
supports_gradient_checkpointing = True
|
| 149 |
+
_no_split_modules = ["WhisperEncoderLayer", "WhisperDecoderLayer", "Gemma2DecoderLayer"]
|
| 150 |
+
_supports_flash_attn_2 = True
|
| 151 |
+
_supports_sdpa = True
|
| 152 |
+
_supports_cache_class = True
|
| 153 |
+
_supports_static_cache = True
|
| 154 |
+
|
| 155 |
+
def _init_weights(self, module):
|
| 156 |
+
# important: this ported version of Qwen2Audio isn't meant for training from scratch - only
|
| 157 |
+
# inference and fine-tuning - so the proper init weights code has been removed
|
| 158 |
+
std = self.config.init_std if hasattr(self.config, "init_std") else self.config.speech_config.init_std
|
| 159 |
+
|
| 160 |
+
if isinstance(module, (nn.Linear, nn.Conv1d)):
|
| 161 |
+
module.weight.data.normal_(mean=0.0, std=std)
|
| 162 |
+
if module.bias is not None:
|
| 163 |
+
module.bias.data.zero_()
|
| 164 |
+
elif isinstance(module, nn.Embedding):
|
| 165 |
+
module.weight.data.normal_(mean=0.0, std=std)
|
| 166 |
+
if module.padding_idx is not None:
|
| 167 |
+
module.weight.data[module.padding_idx].zero_()
|
| 168 |
+
|
| 169 |
+
class MERaLiON3SpeechAudioAdaper(nn.Module):
|
| 170 |
+
def __init__(
|
| 171 |
+
self,
|
| 172 |
+
config,
|
| 173 |
+
**kwargs
|
| 174 |
+
):
|
| 175 |
+
super(MERaLiON3SpeechAudioAdaper, self).__init__()
|
| 176 |
+
speech_audio_encoder_output_dim = config.speech_config.d_model
|
| 177 |
+
llm_input_hidden_size = config.text_config.hidden_size
|
| 178 |
+
speech_mlp_scale_factor = config.speech_mlp_scale_factor
|
| 179 |
+
|
| 180 |
+
self.speech_mlp_scale_factor = speech_mlp_scale_factor
|
| 181 |
+
self.mlp_adapter = nn.Sequential(
|
| 182 |
+
nn.Linear(
|
| 183 |
+
in_features=speech_audio_encoder_output_dim * speech_mlp_scale_factor,
|
| 184 |
+
out_features=speech_audio_encoder_output_dim
|
| 185 |
+
),
|
| 186 |
+
nn.SiLU(),
|
| 187 |
+
nn.Dropout(0.1),
|
| 188 |
+
)
|
| 189 |
+
|
| 190 |
+
self.speech_llm_proj = nn.Sequential(
|
| 191 |
+
nn.Linear(
|
| 192 |
+
speech_audio_encoder_output_dim,
|
| 193 |
+
speech_audio_encoder_output_dim * 4
|
| 194 |
+
),
|
| 195 |
+
nn.SiLU(),
|
| 196 |
+
nn.Dropout(0.1),
|
| 197 |
+
|
| 198 |
+
nn.Linear(
|
| 199 |
+
speech_audio_encoder_output_dim * 4,
|
| 200 |
+
llm_input_hidden_size
|
| 201 |
+
),
|
| 202 |
+
)
|
| 203 |
+
|
| 204 |
+
def forward(self, speech_embeds, **kwargs):
|
| 205 |
+
B, T, C = speech_embeds.shape
|
| 206 |
+
speech_embeds = self.mlp_adapter(
|
| 207 |
+
speech_embeds.reshape(
|
| 208 |
+
B,
|
| 209 |
+
T // self.speech_mlp_scale_factor,
|
| 210 |
+
C * self.speech_mlp_scale_factor,
|
| 211 |
+
)
|
| 212 |
+
)
|
| 213 |
+
return self.speech_llm_proj(speech_embeds)
|
| 214 |
+
|
| 215 |
+
|
| 216 |
+
class MERaLiON3SpeechAudioAdaperLarge(nn.Module):
|
| 217 |
+
def __init__(
|
| 218 |
+
self,
|
| 219 |
+
config,
|
| 220 |
+
**kwargs
|
| 221 |
+
):
|
| 222 |
+
super(MERaLiON3SpeechAudioAdaperLarge, self).__init__()
|
| 223 |
+
speech_audio_encoder_output_dim = config.speech_config.d_model
|
| 224 |
+
llm_input_hidden_size = config.text_config.hidden_size
|
| 225 |
+
|
| 226 |
+
self.speech_mlp_use_projection = config.speech_mlp_use_projection
|
| 227 |
+
self.speech_mlp_scale_factor = config.speech_mlp_scale_factor
|
| 228 |
+
|
| 229 |
+
self.mlp_adapter = nn.Sequential(
|
| 230 |
+
nn.Linear(
|
| 231 |
+
in_features=speech_audio_encoder_output_dim * self.speech_mlp_scale_factor,
|
| 232 |
+
out_features=speech_audio_encoder_output_dim * 5,
|
| 233 |
+
),
|
| 234 |
+
nn.SiLU(),
|
| 235 |
+
nn.Dropout(0.01),
|
| 236 |
+
)
|
| 237 |
+
|
| 238 |
+
if self.speech_mlp_use_projection:
|
| 239 |
+
self.gate_proj = nn.Linear(
|
| 240 |
+
in_features=speech_audio_encoder_output_dim * 5,
|
| 241 |
+
out_features=speech_audio_encoder_output_dim * 5,
|
| 242 |
+
)
|
| 243 |
+
|
| 244 |
+
self.pool_proj = nn.Linear(
|
| 245 |
+
in_features=speech_audio_encoder_output_dim * 5,
|
| 246 |
+
out_features=speech_audio_encoder_output_dim * 5,
|
| 247 |
+
)
|
| 248 |
+
self.act_fn = nn.SiLU()
|
| 249 |
+
|
| 250 |
+
self.out_proj = nn.Linear(
|
| 251 |
+
speech_audio_encoder_output_dim * 5,
|
| 252 |
+
llm_input_hidden_size,
|
| 253 |
+
)
|
| 254 |
+
|
| 255 |
+
|
| 256 |
+
def forward(self, speech_embeds, **kwargs):
|
| 257 |
+
B, T, C = speech_embeds.shape
|
| 258 |
+
speech_embeds = self.mlp_adapter(
|
| 259 |
+
speech_embeds.reshape(
|
| 260 |
+
B,
|
| 261 |
+
T // self.speech_mlp_scale_factor,
|
| 262 |
+
C * self.speech_mlp_scale_factor,
|
| 263 |
+
)
|
| 264 |
+
)
|
| 265 |
+
if self.speech_mlp_use_projection:
|
| 266 |
+
speech_embeds = self.act_fn(self.gate_proj(speech_embeds)) * self.pool_proj(speech_embeds)
|
| 267 |
+
speech_embeds = self.out_proj(speech_embeds)
|
| 268 |
+
return speech_embeds
|
| 269 |
+
|
| 270 |
+
|
| 271 |
+
MERALION_INPUTS_DOCSTRING = r"""
|
| 272 |
+
Args:
|
| 273 |
+
input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`):
|
| 274 |
+
Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide
|
| 275 |
+
it.
|
| 276 |
+
|
| 277 |
+
Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
|
| 278 |
+
[`PreTrainedTokenizer.__call__`] for details.
|
| 279 |
+
|
| 280 |
+
[What are input IDs?](../glossary#input-ids)
|
| 281 |
+
input_features (`torch.FloatTensor` of shape `(batch_size, feature_size, feature_sequence_length)`, *optional*):
|
| 282 |
+
Float values mel features extracted from the raw speech waveform. Raw speech waveform can be obtained by
|
| 283 |
+
loading a `.flac` or `.wav` audio file into an array of type `List[float]` or a `numpy.ndarray`, *e.g.* via
|
| 284 |
+
the soundfile library (`pip install soundfile`). To prepare the array into `input_features`, the
|
| 285 |
+
[`AutoFeatureExtractor`] should be used for extracting the mel features, padding and conversion into a
|
| 286 |
+
tensor of type `torch.FloatTensor`. See [`~WhisperFeatureExtractor.__call__`]
|
| 287 |
+
attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
|
| 288 |
+
Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
|
| 289 |
+
|
| 290 |
+
- 1 for tokens that are **not masked**,
|
| 291 |
+
- 0 for tokens that are **masked**.
|
| 292 |
+
|
| 293 |
+
[What are attention masks?](../glossary#attention-mask)
|
| 294 |
+
|
| 295 |
+
Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
|
| 296 |
+
[`PreTrainedTokenizer.__call__`] for details.
|
| 297 |
+
|
| 298 |
+
If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see
|
| 299 |
+
`past_key_values`).
|
| 300 |
+
|
| 301 |
+
If you want to change padding behavior, you should read [`modeling_opt._prepare_decoder_attention_mask`]
|
| 302 |
+
and modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more
|
| 303 |
+
information on the default strategy.
|
| 304 |
+
|
| 305 |
+
- 1 indicates the head is **not masked**,
|
| 306 |
+
- 0 indicates the head is **masked**.
|
| 307 |
+
feature_attention_mask (`torch.Tensor` of shape `(batch_size, feature_sequence_length)`, *optional*):
|
| 308 |
+
Mask to avoid performing attention on padding feature indices. Mask values selected in `[0, 1]`:
|
| 309 |
+
|
| 310 |
+
- 1 for tokens that are **not masked**,
|
| 311 |
+
- 0 for tokens that are **masked**.
|
| 312 |
+
position_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
|
| 313 |
+
Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0,
|
| 314 |
+
config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids)
|
| 315 |
+
past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
|
| 316 |
+
Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape
|
| 317 |
+
`(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape
|
| 318 |
+
`(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.
|
| 319 |
+
|
| 320 |
+
Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
|
| 321 |
+
blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
|
| 322 |
+
|
| 323 |
+
If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
|
| 324 |
+
don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
|
| 325 |
+
`decoder_input_ids` of shape `(batch_size, sequence_length)`.
|
| 326 |
+
inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
|
| 327 |
+
Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
|
| 328 |
+
is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
|
| 329 |
+
model's internal embedding lookup matrix.
|
| 330 |
+
use_cache (`bool`, *optional*):
|
| 331 |
+
If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
|
| 332 |
+
`past_key_values`).
|
| 333 |
+
output_attentions (`bool`, *optional*):
|
| 334 |
+
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
|
| 335 |
+
tensors for more detail.
|
| 336 |
+
output_hidden_states (`bool`, *optional*):
|
| 337 |
+
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
|
| 338 |
+
more detail.
|
| 339 |
+
return_dict (`bool`, *optional*):
|
| 340 |
+
Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
|
| 341 |
+
"""
|
| 342 |
+
|
| 343 |
+
@add_start_docstrings(
|
| 344 |
+
"""The MERALION model which consists of a audio backbone and a language model.""",
|
| 345 |
+
MERALION_START_DOCSTRING,
|
| 346 |
+
)
|
| 347 |
+
class MERaLiON3ForConditionalGeneration(MERaLiON3PreTrainedModel, GenerationMixin):
|
| 348 |
+
def __init__(self, config: MERaLiON3Config):
|
| 349 |
+
config.text_config._attn_implementation = config._attn_implementation
|
| 350 |
+
config.speech_config._attn_implementation = config._attn_implementation
|
| 351 |
+
|
| 352 |
+
super().__init__(config)
|
| 353 |
+
|
| 354 |
+
self.speech_encoder = WhisperEncoder(config.speech_config)
|
| 355 |
+
# self.speech_encoder = AutoModel.from_config(config.audio_config, attn_implementation=config._attn_implementation)
|
| 356 |
+
|
| 357 |
+
self.ln_speech = nn.LayerNorm(config.speech_config.d_model)
|
| 358 |
+
self.speech_audio_adapter = MERaLiON3SpeechAudioAdaperLarge(config)
|
| 359 |
+
self.vocab_size = config.text_config.vocab_size
|
| 360 |
+
self.text_decoder = Gemma2ForCausalLM(config.text_config)
|
| 361 |
+
self.pad_token_id = self.config.pad_token_id if self.config.pad_token_id is not None else -1
|
| 362 |
+
self._padding_side = "left" # set it to left by default, user can use setter to change padding_sides
|
| 363 |
+
self.post_init()
|
| 364 |
+
|
| 365 |
+
@property
|
| 366 |
+
def padding_side(self):
|
| 367 |
+
return self._padding_side
|
| 368 |
+
|
| 369 |
+
@padding_side.setter
|
| 370 |
+
def padding_side(self, padding_side: str):
|
| 371 |
+
if padding_side not in ["left", "right"]:
|
| 372 |
+
raise ValueError(f"{padding_side} is not `left` or `right`.")
|
| 373 |
+
self._padding_side = padding_side
|
| 374 |
+
|
| 375 |
+
# Copied from transformers.models.llava.modeling_llava.LlavaForConditionalGeneration.get_input_embeddings
|
| 376 |
+
def get_input_embeddings(self):
|
| 377 |
+
return self.text_decoder.get_input_embeddings()
|
| 378 |
+
|
| 379 |
+
# Copied from transformers.models.llava.modeling_llava.LlavaForConditionalGeneration.set_input_embeddings
|
| 380 |
+
def set_input_embeddings(self, value):
|
| 381 |
+
self.text_decoder.set_input_embeddings(value)
|
| 382 |
+
|
| 383 |
+
# Copied from transformers.models.llava.modeling_llava.LlavaForConditionalGeneration.get_output_embeddings
|
| 384 |
+
def get_output_embeddings(self):
|
| 385 |
+
return self.text_decoder.get_output_embeddings()
|
| 386 |
+
|
| 387 |
+
# Copied from transformers.models.llava.modeling_llava.LlavaForConditionalGeneration.set_output_embeddings
|
| 388 |
+
def set_output_embeddings(self, new_embeddings):
|
| 389 |
+
self.text_decoder.set_output_embeddings(new_embeddings)
|
| 390 |
+
|
| 391 |
+
# Copied from transformers.models.llava.modeling_llava.LlavaForConditionalGeneration.set_decoder
|
| 392 |
+
def set_decoder(self, decoder):
|
| 393 |
+
self.text_decoder.set_decoder(decoder)
|
| 394 |
+
|
| 395 |
+
# Copied from transformers.models.llava.modeling_llava.LlavaForConditionalGeneration.get_decoder
|
| 396 |
+
def get_decoder(self):
|
| 397 |
+
return self.text_decoder.get_decoder()
|
| 398 |
+
|
| 399 |
+
# Copied from transformers.models.llava.modeling_llava.LlavaForConditionalGeneration.tie_weights
|
| 400 |
+
def tie_weights(self):
|
| 401 |
+
return self.text_decoder.tie_weights()
|
| 402 |
+
|
| 403 |
+
# Copied from transformers.models.llava.modeling_llava.LlavaForConditionalGeneration.resize_token_embeddings
|
| 404 |
+
def resize_token_embeddings(self, new_num_tokens: Optional[int] = None, pad_to_multiple_of=None) -> nn.Embedding:
|
| 405 |
+
model_embeds = self.text_decoder.resize_token_embeddings(new_num_tokens, pad_to_multiple_of)
|
| 406 |
+
# update vocab size
|
| 407 |
+
self.config.text_config.vocab_size = model_embeds.num_embeddings
|
| 408 |
+
self.vocab_size = model_embeds.num_embeddings
|
| 409 |
+
return model_embeds
|
| 410 |
+
|
| 411 |
+
@add_start_docstrings_to_model_forward(MERALION_INPUTS_DOCSTRING)
|
| 412 |
+
@replace_return_docstrings(output_type=MERaLiON3OutputWithPast, config_class=_CONFIG_FOR_DOC)
|
| 413 |
+
def forward(
|
| 414 |
+
self,
|
| 415 |
+
input_ids: torch.LongTensor = None,
|
| 416 |
+
input_features: torch.FloatTensor = None,
|
| 417 |
+
attention_mask: Optional[torch.Tensor] = None,
|
| 418 |
+
feature_attention_mask: Optional[torch.Tensor] = None,
|
| 419 |
+
position_ids: Optional[torch.LongTensor] = None,
|
| 420 |
+
past_key_values: Optional[List[torch.FloatTensor]] = None,
|
| 421 |
+
inputs_embeds: Optional[torch.FloatTensor] = None,
|
| 422 |
+
labels: Optional[torch.LongTensor] = None,
|
| 423 |
+
use_cache: Optional[bool] = None,
|
| 424 |
+
cache_position: Optional[torch.LongTensor] = None,
|
| 425 |
+
output_attentions: Optional[bool] = None,
|
| 426 |
+
output_hidden_states: Optional[bool] = None,
|
| 427 |
+
return_dict: Optional[bool] = None,
|
| 428 |
+
) -> Union[Tuple, MERaLiON3OutputWithPast]:
|
| 429 |
+
r"""
|
| 430 |
+
Args:
|
| 431 |
+
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
|
| 432 |
+
Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
|
| 433 |
+
config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
|
| 434 |
+
(masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
|
| 435 |
+
|
| 436 |
+
Returns:
|
| 437 |
+
"""
|
| 438 |
+
|
| 439 |
+
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
|
| 440 |
+
output_hidden_states = (
|
| 441 |
+
output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
|
| 442 |
+
)
|
| 443 |
+
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
|
| 444 |
+
|
| 445 |
+
speech_encoder_device = self.speech_encoder.device
|
| 446 |
+
|
| 447 |
+
if input_features is not None:
|
| 448 |
+
input_features = input_features.to(speech_encoder_device)
|
| 449 |
+
feature_attention_mask = feature_attention_mask.to(speech_encoder_device)
|
| 450 |
+
|
| 451 |
+
if inputs_embeds is None:
|
| 452 |
+
speech_contexts_embeds = self.speech_encoder(input_features, attention_mask=feature_attention_mask).last_hidden_state
|
| 453 |
+
speech_contexts_embeds = self.ln_speech(speech_contexts_embeds)
|
| 454 |
+
speech_audio_contexts_embeds = self.speech_audio_adapter(speech_contexts_embeds)
|
| 455 |
+
|
| 456 |
+
inputs_embeds = self.text_decoder.base_model.embed_tokens(input_ids)
|
| 457 |
+
|
| 458 |
+
speech_mask = (input_ids == self.config.speech_token_index).unsqueeze(-1)
|
| 459 |
+
speech_mask = speech_mask.expand_as(inputs_embeds).to(inputs_embeds.device)
|
| 460 |
+
|
| 461 |
+
inputs_embeds = inputs_embeds.masked_scatter(speech_mask, speech_audio_contexts_embeds)
|
| 462 |
+
|
| 463 |
+
input_ids = None
|
| 464 |
+
|
| 465 |
+
outputs = self.text_decoder(
|
| 466 |
+
input_ids=input_ids,
|
| 467 |
+
attention_mask=attention_mask,
|
| 468 |
+
position_ids=position_ids,
|
| 469 |
+
past_key_values=past_key_values,
|
| 470 |
+
inputs_embeds=inputs_embeds,
|
| 471 |
+
use_cache=use_cache,
|
| 472 |
+
cache_position=cache_position,
|
| 473 |
+
output_attentions=output_attentions,
|
| 474 |
+
output_hidden_states=output_hidden_states,
|
| 475 |
+
return_dict=return_dict,
|
| 476 |
+
labels=labels
|
| 477 |
+
)
|
| 478 |
+
|
| 479 |
+
return outputs
|
| 480 |
+
|
| 481 |
+
# from transformers.models.gemma2.modeling_gemma2.Gemma2ForCausalLM.prepare_inputs_for_generation
|
| 482 |
+
def prepare_inputs_for_generation(
|
| 483 |
+
self,
|
| 484 |
+
input_ids,
|
| 485 |
+
attention_mask=None,
|
| 486 |
+
input_features=None,
|
| 487 |
+
feature_attention_mask=None,
|
| 488 |
+
past_key_values=None,
|
| 489 |
+
inputs_embeds=None,
|
| 490 |
+
cache_position=None,
|
| 491 |
+
position_ids=None,
|
| 492 |
+
use_cache=None,
|
| 493 |
+
**kwargs,
|
| 494 |
+
):
|
| 495 |
+
# If we have cache: let's slice `input_ids` through `cache_position`, to keep only the unprocessed tokens
|
| 496 |
+
# Exception 1: when passing input_embeds, input_ids may be missing entries
|
| 497 |
+
# Exception 2: some generation methods do special slicing of input_ids, so we don't need to do it here
|
| 498 |
+
is_first_step = cache_position[0].item() == 0
|
| 499 |
+
if past_key_values is not None:
|
| 500 |
+
if inputs_embeds is not None: # Exception 1
|
| 501 |
+
input_ids = input_ids[:, -cache_position.shape[0] :]
|
| 502 |
+
elif input_ids.shape[1] != cache_position.shape[0]: # Default case (the "else", a no op, is Exception 2)
|
| 503 |
+
input_ids = input_ids[:, cache_position]
|
| 504 |
+
|
| 505 |
+
if attention_mask is not None and position_ids is None:
|
| 506 |
+
# create position_ids on the fly for batch generation
|
| 507 |
+
position_ids = attention_mask.long().cumsum(-1) - 1
|
| 508 |
+
position_ids.masked_fill_(attention_mask == 0, 1)
|
| 509 |
+
if past_key_values:
|
| 510 |
+
position_ids = position_ids[:, -input_ids.shape[1] :]
|
| 511 |
+
# This `clone` call is needed to avoid recapturing cuda graphs with `torch.compile`'s
|
| 512 |
+
# `mode="reduce-overhead`, as otherwise the input `position_ids` would have various stride
|
| 513 |
+
# during the decoding. Here, simply using `.contiguous()` is not sufficient as in the
|
| 514 |
+
# batch size = 1 case, `position_ids` is already contiguous but with varying stride
|
| 515 |
+
# which retriggers a capture.
|
| 516 |
+
position_ids = position_ids.clone(memory_format=torch.contiguous_format)
|
| 517 |
+
|
| 518 |
+
# if `inputs_embeds` are passed, we only want to use them in the 1st generation step
|
| 519 |
+
if inputs_embeds is not None and is_first_step:
|
| 520 |
+
model_inputs = {"inputs_embeds": inputs_embeds, "input_ids": None}
|
| 521 |
+
else:
|
| 522 |
+
# The clone here is for the same reason as for `position_ids`.
|
| 523 |
+
model_inputs = {"input_ids": input_ids.clone(memory_format=torch.contiguous_format), "inputs_embeds": None}
|
| 524 |
+
|
| 525 |
+
if (
|
| 526 |
+
isinstance(past_key_values, HybridCache)
|
| 527 |
+
and attention_mask.ndim == 2
|
| 528 |
+
and not self.config._attn_implementation == "flash_attention_2"
|
| 529 |
+
):
|
| 530 |
+
if model_inputs["inputs_embeds"] is not None:
|
| 531 |
+
batch_size, sequence_length, _ = model_inputs["inputs_embeds"].shape
|
| 532 |
+
device = model_inputs["inputs_embeds"].device
|
| 533 |
+
else:
|
| 534 |
+
batch_size, sequence_length = model_inputs["input_ids"].shape
|
| 535 |
+
device = model_inputs["input_ids"].device
|
| 536 |
+
dtype = self.text_decoder.lm_head.weight.dtype
|
| 537 |
+
min_dtype = torch.finfo(dtype).min
|
| 538 |
+
attention_mask = _prepare_4d_causal_attention_mask_with_cache_position(
|
| 539 |
+
attention_mask,
|
| 540 |
+
sequence_length=sequence_length,
|
| 541 |
+
target_length=past_key_values.get_max_cache_shape(),
|
| 542 |
+
dtype=dtype,
|
| 543 |
+
device=device,
|
| 544 |
+
min_dtype=min_dtype,
|
| 545 |
+
cache_position=cache_position,
|
| 546 |
+
batch_size=batch_size,
|
| 547 |
+
)
|
| 548 |
+
|
| 549 |
+
model_inputs.update(
|
| 550 |
+
{
|
| 551 |
+
"attention_mask": attention_mask,
|
| 552 |
+
"position_ids": position_ids,
|
| 553 |
+
"cache_position": cache_position,
|
| 554 |
+
"past_key_values": past_key_values,
|
| 555 |
+
"use_cache": use_cache
|
| 556 |
+
}
|
| 557 |
+
)
|
| 558 |
+
|
| 559 |
+
# Input ids will only be used from the second step.
|
| 560 |
+
if is_first_step:
|
| 561 |
+
model_inputs["input_features"] = input_features
|
| 562 |
+
model_inputs["feature_attention_mask"] = feature_attention_mask
|
| 563 |
+
|
| 564 |
+
return model_inputs
|
| 565 |
+
|
| 566 |
+
def _reorder_cache(self, *args, **kwargs):
|
| 567 |
+
return self.text_decoder._reorder_cache(*args, **kwargs)
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoProcessor": "processing_meralion3.MERaLiON3Processor"
|
| 4 |
+
},
|
| 5 |
+
"chunk_length": 30,
|
| 6 |
+
"dither": 0.0,
|
| 7 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 8 |
+
"feature_size": 128,
|
| 9 |
+
"hop_length": 160,
|
| 10 |
+
"n_fft": 400,
|
| 11 |
+
"n_samples": 480000,
|
| 12 |
+
"nb_max_frames": 3000,
|
| 13 |
+
"padding_side": "right",
|
| 14 |
+
"padding_value": 0.0,
|
| 15 |
+
"processor_class": "MERaLiON3Processor",
|
| 16 |
+
"return_attention_mask": false,
|
| 17 |
+
"sampling_rate": 16000
|
| 18 |
+
}
|
processing_meralion3.py
ADDED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Processor class for MERaLiON3."""
|
| 2 |
+
|
| 3 |
+
from typing import List, Optional, Union
|
| 4 |
+
|
| 5 |
+
import numpy as np
|
| 6 |
+
|
| 7 |
+
from transformers.feature_extraction_utils import BatchFeature
|
| 8 |
+
from transformers.processing_utils import ProcessorMixin
|
| 9 |
+
from transformers.tokenization_utils_base import PaddingStrategy, PreTokenizedInput, TextInput
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
# copied from transformers.models.qwen2_audio.processing_qwen2_audio.Qwen2AudioProcessor
|
| 13 |
+
class MERaLiON3Processor(ProcessorMixin):
|
| 14 |
+
r"""
|
| 15 |
+
Constructs a MERaLiON3 processor which wraps a whisper feature extractor and a gemma tokenizer into a single processor.
|
| 16 |
+
|
| 17 |
+
[`MERaLiON3Processor`] offers all the functionalities of [`WhisperFeatureExtractor`] and [`GemmaTokenizer`]. See the
|
| 18 |
+
[`~MERaLiON3Processor.__call__`] and [`~MERaLiON3Processor.decode`] for more information.
|
| 19 |
+
|
| 20 |
+
Args:
|
| 21 |
+
feature_extractor ([`WhisperFeatureExtractor`], *optional*):
|
| 22 |
+
The feature extractor is a required input.
|
| 23 |
+
tokenizer ([`GemmaTokenizer`], *optional*):
|
| 24 |
+
The tokenizer is a required input.
|
| 25 |
+
chat_template (`Optional[str]`, *optional*):
|
| 26 |
+
The Jinja template to use for formatting the conversation. If not provided, the default chat template
|
| 27 |
+
is used.
|
| 28 |
+
"""
|
| 29 |
+
|
| 30 |
+
attributes = ["feature_extractor", "tokenizer"]
|
| 31 |
+
feature_extractor_class = "WhisperFeatureExtractor"
|
| 32 |
+
tokenizer_class = "AutoTokenizer"
|
| 33 |
+
valid_kwargs = [
|
| 34 |
+
"fixed_speech_embeds_length",
|
| 35 |
+
"speech_token_index",
|
| 36 |
+
"time_duration_limit",
|
| 37 |
+
"whisper_chunk_size",
|
| 38 |
+
"do_normalize"
|
| 39 |
+
]
|
| 40 |
+
|
| 41 |
+
def __init__(
|
| 42 |
+
self,
|
| 43 |
+
feature_extractor=None,
|
| 44 |
+
tokenizer=None,
|
| 45 |
+
fixed_speech_embeds_length=100,
|
| 46 |
+
speech_token_index=255999,
|
| 47 |
+
time_duration_limit=300,
|
| 48 |
+
whisper_chunk_size=30,
|
| 49 |
+
do_normalize=True
|
| 50 |
+
):
|
| 51 |
+
self.fixed_speech_embeds_length = fixed_speech_embeds_length
|
| 52 |
+
self.speech_token_index = speech_token_index
|
| 53 |
+
self.time_duration_limit = time_duration_limit
|
| 54 |
+
self.whisper_chunk_size = whisper_chunk_size
|
| 55 |
+
self.number_chunk_limit = self.time_duration_limit // self.whisper_chunk_size
|
| 56 |
+
self.do_normalize = do_normalize
|
| 57 |
+
|
| 58 |
+
super().__init__(feature_extractor, tokenizer)
|
| 59 |
+
|
| 60 |
+
self.speech_token = self.tokenizer.added_tokens_decoder[self.speech_token_index].content
|
| 61 |
+
self.feature_chunk_size = self.whisper_chunk_size * self.feature_extractor.sampling_rate
|
| 62 |
+
|
| 63 |
+
def _process_text(self, text: List[str], audio_number_chunks: np.ndarray):
|
| 64 |
+
pieces = []
|
| 65 |
+
for i, item in enumerate(text):
|
| 66 |
+
target_string = self.speech_token * self.fixed_speech_embeds_length * audio_number_chunks[i]
|
| 67 |
+
pieces.append(item.replace(self.speech_token, target_string))
|
| 68 |
+
return pieces
|
| 69 |
+
|
| 70 |
+
def _get_number_chunks(self, audios: List[np.ndarray]):
|
| 71 |
+
audio_lengths = np.array([_.shape[0] for _ in audios])
|
| 72 |
+
number_chunks = ((audio_lengths - 1) // self.feature_chunk_size) + 1
|
| 73 |
+
return np.clip(number_chunks, a_min=None, a_max=self.number_chunk_limit)
|
| 74 |
+
|
| 75 |
+
def _get_chunked_audios(self, audios: Union[np.ndarray, List[np.ndarray]]):
|
| 76 |
+
if isinstance(audios, np.ndarray):
|
| 77 |
+
audios = [audios]
|
| 78 |
+
|
| 79 |
+
audio_number_chunks = self._get_number_chunks(audios)
|
| 80 |
+
chunked_audios = []
|
| 81 |
+
|
| 82 |
+
for audio_idx, audio in enumerate(audios):
|
| 83 |
+
for cid in range(audio_number_chunks[audio_idx]):
|
| 84 |
+
chunked_audios.append(
|
| 85 |
+
audio[cid * self.feature_chunk_size: (cid + 1) * self.feature_chunk_size]
|
| 86 |
+
)
|
| 87 |
+
return audio_number_chunks, chunked_audios
|
| 88 |
+
|
| 89 |
+
def __call__(
|
| 90 |
+
self,
|
| 91 |
+
text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
|
| 92 |
+
audios: Union[np.ndarray, List[np.ndarray]] = None,
|
| 93 |
+
padding: Union[bool, str, PaddingStrategy] = True,
|
| 94 |
+
sampling_rate: Optional[int] = None,
|
| 95 |
+
do_normalize: Optional[bool] = None,
|
| 96 |
+
**kwargs,
|
| 97 |
+
) -> BatchFeature:
|
| 98 |
+
"""
|
| 99 |
+
Main method to prepare for the model one or several sequences(s) and audio(s). This method forwards the `text`
|
| 100 |
+
and `kwargs` arguments to GemmaTokenizer's [`~GemmaTokenizer.__call__`] if `text` is not `None` to encode
|
| 101 |
+
the text. To prepare the audio(s), this method forwards the `audios` and `kwrags` arguments to
|
| 102 |
+
WhisperFeatureExtractor's [`~WhisperFeatureExtractor.__call__`] if `audios` is not `None`. Please refer to the doctsring
|
| 103 |
+
of the above two methods for more information.
|
| 104 |
+
|
| 105 |
+
Args:
|
| 106 |
+
text (`str`, `List[str]`):
|
| 107 |
+
The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
|
| 108 |
+
(pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
|
| 109 |
+
`is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
|
| 110 |
+
audios (`np.ndarray`, `List[np.ndarray]`):
|
| 111 |
+
The audio or batch of audios to be prepared. Each audio can be a NumPy array.
|
| 112 |
+
padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`):
|
| 113 |
+
Select a strategy to pad the returned sequences (according to the model's padding side and padding
|
| 114 |
+
index) among:
|
| 115 |
+
- `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
|
| 116 |
+
sequence if provided).
|
| 117 |
+
- `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
|
| 118 |
+
acceptable input length for the model if that argument is not provided.
|
| 119 |
+
- `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
|
| 120 |
+
lengths).
|
| 121 |
+
sampling_rate (`int`, defaults to 16000):
|
| 122 |
+
The sampling rate at which the audio files should be digitalized expressed in hertz (Hz).
|
| 123 |
+
do_normalize (`bool`, defaults to `True`):
|
| 124 |
+
Whether or not to zero-mean unit-variance normalize the input.
|
| 125 |
+
Normalizing can help to significantly improve the performance of the model.
|
| 126 |
+
"""
|
| 127 |
+
|
| 128 |
+
if text is None:
|
| 129 |
+
raise ValueError("You need to specify either a `text` input to process.")
|
| 130 |
+
if not isinstance(text, list):
|
| 131 |
+
text = [text]
|
| 132 |
+
if not isinstance(audios, list):
|
| 133 |
+
audios = [audios]
|
| 134 |
+
if sampling_rate is None:
|
| 135 |
+
sampling_rate = self.feature_extractor.sampling_rate
|
| 136 |
+
if do_normalize is None:
|
| 137 |
+
do_normalize = self.do_normalize
|
| 138 |
+
|
| 139 |
+
for i, audio in enumerate(audios):
|
| 140 |
+
if audio.ndim > 1:
|
| 141 |
+
raise Exception(f"MERaLiON3 only accepts mono channel audio, {i+1}th audio have {audios[0].ndim} channels")
|
| 142 |
+
|
| 143 |
+
inputs_dict = {}
|
| 144 |
+
|
| 145 |
+
if audios is not None:
|
| 146 |
+
audio_number_chunks, chunked_audios = self._get_chunked_audios(audios)
|
| 147 |
+
text = self._process_text(text, audio_number_chunks)
|
| 148 |
+
|
| 149 |
+
audio_inputs = self.feature_extractor(
|
| 150 |
+
chunked_audios,
|
| 151 |
+
sampling_rate=sampling_rate,
|
| 152 |
+
return_tensors="pt",
|
| 153 |
+
return_attention_mask=True,
|
| 154 |
+
padding="max_length",
|
| 155 |
+
do_normalize=self.do_normalize,
|
| 156 |
+
)
|
| 157 |
+
audio_inputs["feature_attention_mask"] = audio_inputs.pop(
|
| 158 |
+
"attention_mask"
|
| 159 |
+
) # rename attention_mask to prevent conflicts later on
|
| 160 |
+
inputs_dict.update(audio_inputs)
|
| 161 |
+
|
| 162 |
+
text_input = self.tokenizer(
|
| 163 |
+
text=text,
|
| 164 |
+
return_tensors="pt",
|
| 165 |
+
add_special_tokens=False,
|
| 166 |
+
return_attention_mask=True,
|
| 167 |
+
padding=padding,
|
| 168 |
+
)
|
| 169 |
+
|
| 170 |
+
inputs_dict["input_ids"] = text_input.input_ids
|
| 171 |
+
inputs_dict["attention_mask"] = text_input.attention_mask
|
| 172 |
+
|
| 173 |
+
return BatchFeature(data={**inputs_dict})
|
| 174 |
+
|
| 175 |
+
def batch_decode(self, *args, **kwargs):
|
| 176 |
+
"""
|
| 177 |
+
This method forwards all its arguments to GemmaTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please
|
| 178 |
+
refer to the docstring of this method for more information.
|
| 179 |
+
"""
|
| 180 |
+
return self.tokenizer.batch_decode(*args, **kwargs)
|
| 181 |
+
|
| 182 |
+
def decode(self, *args, **kwargs):
|
| 183 |
+
"""
|
| 184 |
+
This method forwards all its arguments to GemmaTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to
|
| 185 |
+
the docstring of this method for more information.
|
| 186 |
+
"""
|
| 187 |
+
return self.tokenizer.decode(*args, **kwargs)
|
| 188 |
+
|
| 189 |
+
@property
|
| 190 |
+
def model_input_names(self):
|
| 191 |
+
tokenizer_input_names = self.tokenizer.model_input_names
|
| 192 |
+
feature_extractor_input_names = self.feature_extractor.model_input_names
|
| 193 |
+
return list(dict.fromkeys(tokenizer_input_names + feature_extractor_input_names + ["feature_attention_mask"]))
|
processor_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoProcessor": "processing_meralion3.MERaLiON3Processor"
|
| 4 |
+
},
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"fixed_speech_embeds_length": 300,
|
| 7 |
+
"processor_class": "MERaLiON3Processor",
|
| 8 |
+
"speech_token_index": 255999,
|
| 9 |
+
"time_duration_limit": 300,
|
| 10 |
+
"whisper_chunk_size": 30
|
| 11 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<start_of_turn>",
|
| 4 |
+
"<end_of_turn>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<bos>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<eos>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": {
|
| 21 |
+
"content": "<pad>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ead607d5168e96c02d261dfac8408c63ff2f52e0ac240ac89d0450b3ec805d8
|
| 3 |
+
size 34362877
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
| 3 |
+
size 4241003
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2019 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<pad>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<eos>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<bos>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"4": {
|
| 38 |
+
"content": "<mask>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"5": {
|
| 46 |
+
"content": "<2mass>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"6": {
|
| 54 |
+
"content": "[@BOS@]",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"7": {
|
| 62 |
+
"content": "<unused0>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"8": {
|
| 70 |
+
"content": "<unused1>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"9": {
|
| 78 |
+
"content": "<unused2>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"10": {
|
| 86 |
+
"content": "<unused3>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"11": {
|
| 94 |
+
"content": "<unused4>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"12": {
|
| 102 |
+
"content": "<unused5>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"13": {
|
| 110 |
+
"content": "<unused6>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": false
|
| 116 |
+
},
|
| 117 |
+
"14": {
|
| 118 |
+
"content": "<unused7>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"15": {
|
| 126 |
+
"content": "<unused8>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"16": {
|
| 134 |
+
"content": "<unused9>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"17": {
|
| 142 |
+
"content": "<unused10>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"18": {
|
| 150 |
+
"content": "<unused11>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"19": {
|
| 158 |
+
"content": "<unused12>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"20": {
|
| 166 |
+
"content": "<unused13>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"21": {
|
| 174 |
+
"content": "<unused14>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"22": {
|
| 182 |
+
"content": "<unused15>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"23": {
|
| 190 |
+
"content": "<unused16>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"24": {
|
| 198 |
+
"content": "<unused17>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"25": {
|
| 206 |
+
"content": "<unused18>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"26": {
|
| 214 |
+
"content": "<unused19>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": false
|
| 220 |
+
},
|
| 221 |
+
"27": {
|
| 222 |
+
"content": "<unused20>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": false
|
| 228 |
+
},
|
| 229 |
+
"28": {
|
| 230 |
+
"content": "<unused21>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": false
|
| 236 |
+
},
|
| 237 |
+
"29": {
|
| 238 |
+
"content": "<unused22>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": false
|
| 244 |
+
},
|
| 245 |
+
"30": {
|
| 246 |
+
"content": "<unused23>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": false
|
| 252 |
+
},
|
| 253 |
+
"31": {
|
| 254 |
+
"content": "<unused24>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": false
|
| 260 |
+
},
|
| 261 |
+
"32": {
|
| 262 |
+
"content": "<unused25>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": false
|
| 268 |
+
},
|
| 269 |
+
"33": {
|
| 270 |
+
"content": "<unused26>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": false
|
| 276 |
+
},
|
| 277 |
+
"34": {
|
| 278 |
+
"content": "<unused27>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": false
|
| 284 |
+
},
|
| 285 |
+
"35": {
|
| 286 |
+
"content": "<unused28>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": false
|
| 292 |
+
},
|
| 293 |
+
"36": {
|
| 294 |
+
"content": "<unused29>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": false
|
| 300 |
+
},
|
| 301 |
+
"37": {
|
| 302 |
+
"content": "<unused30>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": false
|
| 308 |
+
},
|
| 309 |
+
"38": {
|
| 310 |
+
"content": "<unused31>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": false
|
| 316 |
+
},
|
| 317 |
+
"39": {
|
| 318 |
+
"content": "<unused32>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": false
|
| 324 |
+
},
|
| 325 |
+
"40": {
|
| 326 |
+
"content": "<unused33>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": false
|
| 332 |
+
},
|
| 333 |
+
"41": {
|
| 334 |
+
"content": "<unused34>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": false
|
| 340 |
+
},
|
| 341 |
+
"42": {
|
| 342 |
+
"content": "<unused35>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": false
|
| 348 |
+
},
|
| 349 |
+
"43": {
|
| 350 |
+
"content": "<unused36>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": false
|
| 356 |
+
},
|
| 357 |
+
"44": {
|
| 358 |
+
"content": "<unused37>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": false
|
| 364 |
+
},
|
| 365 |
+
"45": {
|
| 366 |
+
"content": "<unused38>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": false
|
| 372 |
+
},
|
| 373 |
+
"46": {
|
| 374 |
+
"content": "<unused39>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": false
|
| 380 |
+
},
|
| 381 |
+
"47": {
|
| 382 |
+
"content": "<unused40>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": false
|
| 388 |
+
},
|
| 389 |
+
"48": {
|
| 390 |
+
"content": "<unused41>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": false
|
| 396 |
+
},
|
| 397 |
+
"49": {
|
| 398 |
+
"content": "<unused42>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": false
|
| 404 |
+
},
|
| 405 |
+
"50": {
|
| 406 |
+
"content": "<unused43>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": false
|
| 412 |
+
},
|
| 413 |
+
"51": {
|
| 414 |
+
"content": "<unused44>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": false
|
| 420 |
+
},
|
| 421 |
+
"52": {
|
| 422 |
+
"content": "<unused45>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": false
|
| 428 |
+
},
|
| 429 |
+
"53": {
|
| 430 |
+
"content": "<unused46>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": false
|
| 436 |
+
},
|
| 437 |
+
"54": {
|
| 438 |
+
"content": "<unused47>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": false
|
| 444 |
+
},
|
| 445 |
+
"55": {
|
| 446 |
+
"content": "<unused48>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": false
|
| 452 |
+
},
|
| 453 |
+
"56": {
|
| 454 |
+
"content": "<unused49>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": false
|
| 460 |
+
},
|
| 461 |
+
"57": {
|
| 462 |
+
"content": "<unused50>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": false
|
| 468 |
+
},
|
| 469 |
+
"58": {
|
| 470 |
+
"content": "<unused51>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": false
|
| 476 |
+
},
|
| 477 |
+
"59": {
|
| 478 |
+
"content": "<unused52>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": false
|
| 484 |
+
},
|
| 485 |
+
"60": {
|
| 486 |
+
"content": "<unused53>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": false
|
| 492 |
+
},
|
| 493 |
+
"61": {
|
| 494 |
+
"content": "<unused54>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": false
|
| 500 |
+
},
|
| 501 |
+
"62": {
|
| 502 |
+
"content": "<unused55>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": false,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": false
|
| 508 |
+
},
|
| 509 |
+
"63": {
|
| 510 |
+
"content": "<unused56>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": false
|
| 516 |
+
},
|
| 517 |
+
"64": {
|
| 518 |
+
"content": "<unused57>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": false,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": false
|
| 524 |
+
},
|
| 525 |
+
"65": {
|
| 526 |
+
"content": "<unused58>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": false
|
| 532 |
+
},
|
| 533 |
+
"66": {
|
| 534 |
+
"content": "<unused59>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": false,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": false
|
| 540 |
+
},
|
| 541 |
+
"67": {
|
| 542 |
+
"content": "<unused60>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": false,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": false
|
| 548 |
+
},
|
| 549 |
+
"68": {
|
| 550 |
+
"content": "<unused61>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": false
|
| 556 |
+
},
|
| 557 |
+
"69": {
|
| 558 |
+
"content": "<unused62>",
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"normalized": false,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": false
|
| 564 |
+
},
|
| 565 |
+
"70": {
|
| 566 |
+
"content": "<unused63>",
|
| 567 |
+
"lstrip": false,
|
| 568 |
+
"normalized": false,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": false
|
| 572 |
+
},
|
| 573 |
+
"71": {
|
| 574 |
+
"content": "<unused64>",
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"normalized": false,
|
| 577 |
+
"rstrip": false,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": false
|
| 580 |
+
},
|
| 581 |
+
"72": {
|
| 582 |
+
"content": "<unused65>",
|
| 583 |
+
"lstrip": false,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": false
|
| 588 |
+
},
|
| 589 |
+
"73": {
|
| 590 |
+
"content": "<unused66>",
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"normalized": false,
|
| 593 |
+
"rstrip": false,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": false
|
| 596 |
+
},
|
| 597 |
+
"74": {
|
| 598 |
+
"content": "<unused67>",
|
| 599 |
+
"lstrip": false,
|
| 600 |
+
"normalized": false,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": false
|
| 604 |
+
},
|
| 605 |
+
"75": {
|
| 606 |
+
"content": "<unused68>",
|
| 607 |
+
"lstrip": false,
|
| 608 |
+
"normalized": false,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": false
|
| 612 |
+
},
|
| 613 |
+
"76": {
|
| 614 |
+
"content": "<unused69>",
|
| 615 |
+
"lstrip": false,
|
| 616 |
+
"normalized": false,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": false
|
| 620 |
+
},
|
| 621 |
+
"77": {
|
| 622 |
+
"content": "<unused70>",
|
| 623 |
+
"lstrip": false,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"rstrip": false,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": false
|
| 628 |
+
},
|
| 629 |
+
"78": {
|
| 630 |
+
"content": "<unused71>",
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"normalized": false,
|
| 633 |
+
"rstrip": false,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": false
|
| 636 |
+
},
|
| 637 |
+
"79": {
|
| 638 |
+
"content": "<unused72>",
|
| 639 |
+
"lstrip": false,
|
| 640 |
+
"normalized": false,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": false
|
| 644 |
+
},
|
| 645 |
+
"80": {
|
| 646 |
+
"content": "<unused73>",
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"normalized": false,
|
| 649 |
+
"rstrip": false,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": false
|
| 652 |
+
},
|
| 653 |
+
"81": {
|
| 654 |
+
"content": "<unused74>",
|
| 655 |
+
"lstrip": false,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": false
|
| 660 |
+
},
|
| 661 |
+
"82": {
|
| 662 |
+
"content": "<unused75>",
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"normalized": false,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": false
|
| 668 |
+
},
|
| 669 |
+
"83": {
|
| 670 |
+
"content": "<unused76>",
|
| 671 |
+
"lstrip": false,
|
| 672 |
+
"normalized": false,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": false
|
| 676 |
+
},
|
| 677 |
+
"84": {
|
| 678 |
+
"content": "<unused77>",
|
| 679 |
+
"lstrip": false,
|
| 680 |
+
"normalized": false,
|
| 681 |
+
"rstrip": false,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": false
|
| 684 |
+
},
|
| 685 |
+
"85": {
|
| 686 |
+
"content": "<unused78>",
|
| 687 |
+
"lstrip": false,
|
| 688 |
+
"normalized": false,
|
| 689 |
+
"rstrip": false,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": false
|
| 692 |
+
},
|
| 693 |
+
"86": {
|
| 694 |
+
"content": "<unused79>",
|
| 695 |
+
"lstrip": false,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"rstrip": false,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": false
|
| 700 |
+
},
|
| 701 |
+
"87": {
|
| 702 |
+
"content": "<unused80>",
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"normalized": false,
|
| 705 |
+
"rstrip": false,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": false
|
| 708 |
+
},
|
| 709 |
+
"88": {
|
| 710 |
+
"content": "<unused81>",
|
| 711 |
+
"lstrip": false,
|
| 712 |
+
"normalized": false,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": false
|
| 716 |
+
},
|
| 717 |
+
"89": {
|
| 718 |
+
"content": "<unused82>",
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"normalized": false,
|
| 721 |
+
"rstrip": false,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": false
|
| 724 |
+
},
|
| 725 |
+
"90": {
|
| 726 |
+
"content": "<unused83>",
|
| 727 |
+
"lstrip": false,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": false
|
| 732 |
+
},
|
| 733 |
+
"91": {
|
| 734 |
+
"content": "<unused84>",
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"normalized": false,
|
| 737 |
+
"rstrip": false,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": false
|
| 740 |
+
},
|
| 741 |
+
"92": {
|
| 742 |
+
"content": "<unused85>",
|
| 743 |
+
"lstrip": false,
|
| 744 |
+
"normalized": false,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": false
|
| 748 |
+
},
|
| 749 |
+
"93": {
|
| 750 |
+
"content": "<unused86>",
|
| 751 |
+
"lstrip": false,
|
| 752 |
+
"normalized": false,
|
| 753 |
+
"rstrip": false,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": false
|
| 756 |
+
},
|
| 757 |
+
"94": {
|
| 758 |
+
"content": "<unused87>",
|
| 759 |
+
"lstrip": false,
|
| 760 |
+
"normalized": false,
|
| 761 |
+
"rstrip": false,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": false
|
| 764 |
+
},
|
| 765 |
+
"95": {
|
| 766 |
+
"content": "<unused88>",
|
| 767 |
+
"lstrip": false,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"rstrip": false,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": false
|
| 772 |
+
},
|
| 773 |
+
"96": {
|
| 774 |
+
"content": "<unused89>",
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"normalized": false,
|
| 777 |
+
"rstrip": false,
|
| 778 |
+
"single_word": false,
|
| 779 |
+
"special": false
|
| 780 |
+
},
|
| 781 |
+
"97": {
|
| 782 |
+
"content": "<unused90>",
|
| 783 |
+
"lstrip": false,
|
| 784 |
+
"normalized": false,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"single_word": false,
|
| 787 |
+
"special": false
|
| 788 |
+
},
|
| 789 |
+
"98": {
|
| 790 |
+
"content": "<unused91>",
|
| 791 |
+
"lstrip": false,
|
| 792 |
+
"normalized": false,
|
| 793 |
+
"rstrip": false,
|
| 794 |
+
"single_word": false,
|
| 795 |
+
"special": false
|
| 796 |
+
},
|
| 797 |
+
"99": {
|
| 798 |
+
"content": "<unused92>",
|
| 799 |
+
"lstrip": false,
|
| 800 |
+
"normalized": false,
|
| 801 |
+
"rstrip": false,
|
| 802 |
+
"single_word": false,
|
| 803 |
+
"special": false
|
| 804 |
+
},
|
| 805 |
+
"100": {
|
| 806 |
+
"content": "<unused93>",
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"normalized": false,
|
| 809 |
+
"rstrip": false,
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"special": false
|
| 812 |
+
},
|
| 813 |
+
"101": {
|
| 814 |
+
"content": "<unused94>",
|
| 815 |
+
"lstrip": false,
|
| 816 |
+
"normalized": false,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"single_word": false,
|
| 819 |
+
"special": false
|
| 820 |
+
},
|
| 821 |
+
"102": {
|
| 822 |
+
"content": "<unused95>",
|
| 823 |
+
"lstrip": false,
|
| 824 |
+
"normalized": false,
|
| 825 |
+
"rstrip": false,
|
| 826 |
+
"single_word": false,
|
| 827 |
+
"special": false
|
| 828 |
+
},
|
| 829 |
+
"103": {
|
| 830 |
+
"content": "<unused96>",
|
| 831 |
+
"lstrip": false,
|
| 832 |
+
"normalized": false,
|
| 833 |
+
"rstrip": false,
|
| 834 |
+
"single_word": false,
|
| 835 |
+
"special": false
|
| 836 |
+
},
|
| 837 |
+
"104": {
|
| 838 |
+
"content": "<unused97>",
|
| 839 |
+
"lstrip": false,
|
| 840 |
+
"normalized": false,
|
| 841 |
+
"rstrip": false,
|
| 842 |
+
"single_word": false,
|
| 843 |
+
"special": false
|
| 844 |
+
},
|
| 845 |
+
"105": {
|
| 846 |
+
"content": "<unused98>",
|
| 847 |
+
"lstrip": false,
|
| 848 |
+
"normalized": false,
|
| 849 |
+
"rstrip": false,
|
| 850 |
+
"single_word": false,
|
| 851 |
+
"special": false
|
| 852 |
+
},
|
| 853 |
+
"106": {
|
| 854 |
+
"content": "<start_of_turn>",
|
| 855 |
+
"lstrip": false,
|
| 856 |
+
"normalized": false,
|
| 857 |
+
"rstrip": false,
|
| 858 |
+
"single_word": false,
|
| 859 |
+
"special": true
|
| 860 |
+
},
|
| 861 |
+
"107": {
|
| 862 |
+
"content": "<end_of_turn>",
|
| 863 |
+
"lstrip": false,
|
| 864 |
+
"normalized": false,
|
| 865 |
+
"rstrip": false,
|
| 866 |
+
"single_word": false,
|
| 867 |
+
"special": true
|
| 868 |
+
},
|
| 869 |
+
"108": {
|
| 870 |
+
"content": "\n",
|
| 871 |
+
"lstrip": false,
|
| 872 |
+
"normalized": false,
|
| 873 |
+
"rstrip": false,
|
| 874 |
+
"single_word": false,
|
| 875 |
+
"special": false
|
| 876 |
+
},
|
| 877 |
+
"109": {
|
| 878 |
+
"content": "\n\n",
|
| 879 |
+
"lstrip": false,
|
| 880 |
+
"normalized": false,
|
| 881 |
+
"rstrip": false,
|
| 882 |
+
"single_word": false,
|
| 883 |
+
"special": false
|
| 884 |
+
},
|
| 885 |
+
"110": {
|
| 886 |
+
"content": "\n\n\n",
|
| 887 |
+
"lstrip": false,
|
| 888 |
+
"normalized": false,
|
| 889 |
+
"rstrip": false,
|
| 890 |
+
"single_word": false,
|
| 891 |
+
"special": false
|
| 892 |
+
},
|
| 893 |
+
"111": {
|
| 894 |
+
"content": "\n\n\n\n",
|
| 895 |
+
"lstrip": false,
|
| 896 |
+
"normalized": false,
|
| 897 |
+
"rstrip": false,
|
| 898 |
+
"single_word": false,
|
| 899 |
+
"special": false
|
| 900 |
+
},
|
| 901 |
+
"112": {
|
| 902 |
+
"content": "\n\n\n\n\n",
|
| 903 |
+
"lstrip": false,
|
| 904 |
+
"normalized": false,
|
| 905 |
+
"rstrip": false,
|
| 906 |
+
"single_word": false,
|
| 907 |
+
"special": false
|
| 908 |
+
},
|
| 909 |
+
"113": {
|
| 910 |
+
"content": "\n\n\n\n\n\n",
|
| 911 |
+
"lstrip": false,
|
| 912 |
+
"normalized": false,
|
| 913 |
+
"rstrip": false,
|
| 914 |
+
"single_word": false,
|
| 915 |
+
"special": false
|
| 916 |
+
},
|
| 917 |
+
"114": {
|
| 918 |
+
"content": "\n\n\n\n\n\n\n",
|
| 919 |
+
"lstrip": false,
|
| 920 |
+
"normalized": false,
|
| 921 |
+
"rstrip": false,
|
| 922 |
+
"single_word": false,
|
| 923 |
+
"special": false
|
| 924 |
+
},
|
| 925 |
+
"115": {
|
| 926 |
+
"content": "\n\n\n\n\n\n\n\n",
|
| 927 |
+
"lstrip": false,
|
| 928 |
+
"normalized": false,
|
| 929 |
+
"rstrip": false,
|
| 930 |
+
"single_word": false,
|
| 931 |
+
"special": false
|
| 932 |
+
},
|
| 933 |
+
"116": {
|
| 934 |
+
"content": "\n\n\n\n\n\n\n\n\n",
|
| 935 |
+
"lstrip": false,
|
| 936 |
+
"normalized": false,
|
| 937 |
+
"rstrip": false,
|
| 938 |
+
"single_word": false,
|
| 939 |
+
"special": false
|
| 940 |
+
},
|
| 941 |
+
"117": {
|
| 942 |
+
"content": "\n\n\n\n\n\n\n\n\n\n",
|
| 943 |
+
"lstrip": false,
|
| 944 |
+
"normalized": false,
|
| 945 |
+
"rstrip": false,
|
| 946 |
+
"single_word": false,
|
| 947 |
+
"special": false
|
| 948 |
+
},
|
| 949 |
+
"118": {
|
| 950 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n",
|
| 951 |
+
"lstrip": false,
|
| 952 |
+
"normalized": false,
|
| 953 |
+
"rstrip": false,
|
| 954 |
+
"single_word": false,
|
| 955 |
+
"special": false
|
| 956 |
+
},
|
| 957 |
+
"119": {
|
| 958 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 959 |
+
"lstrip": false,
|
| 960 |
+
"normalized": false,
|
| 961 |
+
"rstrip": false,
|
| 962 |
+
"single_word": false,
|
| 963 |
+
"special": false
|
| 964 |
+
},
|
| 965 |
+
"120": {
|
| 966 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 967 |
+
"lstrip": false,
|
| 968 |
+
"normalized": false,
|
| 969 |
+
"rstrip": false,
|
| 970 |
+
"single_word": false,
|
| 971 |
+
"special": false
|
| 972 |
+
},
|
| 973 |
+
"121": {
|
| 974 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 975 |
+
"lstrip": false,
|
| 976 |
+
"normalized": false,
|
| 977 |
+
"rstrip": false,
|
| 978 |
+
"single_word": false,
|
| 979 |
+
"special": false
|
| 980 |
+
},
|
| 981 |
+
"122": {
|
| 982 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 983 |
+
"lstrip": false,
|
| 984 |
+
"normalized": false,
|
| 985 |
+
"rstrip": false,
|
| 986 |
+
"single_word": false,
|
| 987 |
+
"special": false
|
| 988 |
+
},
|
| 989 |
+
"123": {
|
| 990 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 991 |
+
"lstrip": false,
|
| 992 |
+
"normalized": false,
|
| 993 |
+
"rstrip": false,
|
| 994 |
+
"single_word": false,
|
| 995 |
+
"special": false
|
| 996 |
+
},
|
| 997 |
+
"124": {
|
| 998 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 999 |
+
"lstrip": false,
|
| 1000 |
+
"normalized": false,
|
| 1001 |
+
"rstrip": false,
|
| 1002 |
+
"single_word": false,
|
| 1003 |
+
"special": false
|
| 1004 |
+
},
|
| 1005 |
+
"125": {
|
| 1006 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1007 |
+
"lstrip": false,
|
| 1008 |
+
"normalized": false,
|
| 1009 |
+
"rstrip": false,
|
| 1010 |
+
"single_word": false,
|
| 1011 |
+
"special": false
|
| 1012 |
+
},
|
| 1013 |
+
"126": {
|
| 1014 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1015 |
+
"lstrip": false,
|
| 1016 |
+
"normalized": false,
|
| 1017 |
+
"rstrip": false,
|
| 1018 |
+
"single_word": false,
|
| 1019 |
+
"special": false
|
| 1020 |
+
},
|
| 1021 |
+
"127": {
|
| 1022 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1023 |
+
"lstrip": false,
|
| 1024 |
+
"normalized": false,
|
| 1025 |
+
"rstrip": false,
|
| 1026 |
+
"single_word": false,
|
| 1027 |
+
"special": false
|
| 1028 |
+
},
|
| 1029 |
+
"128": {
|
| 1030 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1031 |
+
"lstrip": false,
|
| 1032 |
+
"normalized": false,
|
| 1033 |
+
"rstrip": false,
|
| 1034 |
+
"single_word": false,
|
| 1035 |
+
"special": false
|
| 1036 |
+
},
|
| 1037 |
+
"129": {
|
| 1038 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1039 |
+
"lstrip": false,
|
| 1040 |
+
"normalized": false,
|
| 1041 |
+
"rstrip": false,
|
| 1042 |
+
"single_word": false,
|
| 1043 |
+
"special": false
|
| 1044 |
+
},
|
| 1045 |
+
"130": {
|
| 1046 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1047 |
+
"lstrip": false,
|
| 1048 |
+
"normalized": false,
|
| 1049 |
+
"rstrip": false,
|
| 1050 |
+
"single_word": false,
|
| 1051 |
+
"special": false
|
| 1052 |
+
},
|
| 1053 |
+
"131": {
|
| 1054 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1055 |
+
"lstrip": false,
|
| 1056 |
+
"normalized": false,
|
| 1057 |
+
"rstrip": false,
|
| 1058 |
+
"single_word": false,
|
| 1059 |
+
"special": false
|
| 1060 |
+
},
|
| 1061 |
+
"132": {
|
| 1062 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1063 |
+
"lstrip": false,
|
| 1064 |
+
"normalized": false,
|
| 1065 |
+
"rstrip": false,
|
| 1066 |
+
"single_word": false,
|
| 1067 |
+
"special": false
|
| 1068 |
+
},
|
| 1069 |
+
"133": {
|
| 1070 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1071 |
+
"lstrip": false,
|
| 1072 |
+
"normalized": false,
|
| 1073 |
+
"rstrip": false,
|
| 1074 |
+
"single_word": false,
|
| 1075 |
+
"special": false
|
| 1076 |
+
},
|
| 1077 |
+
"134": {
|
| 1078 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1079 |
+
"lstrip": false,
|
| 1080 |
+
"normalized": false,
|
| 1081 |
+
"rstrip": false,
|
| 1082 |
+
"single_word": false,
|
| 1083 |
+
"special": false
|
| 1084 |
+
},
|
| 1085 |
+
"135": {
|
| 1086 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1087 |
+
"lstrip": false,
|
| 1088 |
+
"normalized": false,
|
| 1089 |
+
"rstrip": false,
|
| 1090 |
+
"single_word": false,
|
| 1091 |
+
"special": false
|
| 1092 |
+
},
|
| 1093 |
+
"136": {
|
| 1094 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1095 |
+
"lstrip": false,
|
| 1096 |
+
"normalized": false,
|
| 1097 |
+
"rstrip": false,
|
| 1098 |
+
"single_word": false,
|
| 1099 |
+
"special": false
|
| 1100 |
+
},
|
| 1101 |
+
"137": {
|
| 1102 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1103 |
+
"lstrip": false,
|
| 1104 |
+
"normalized": false,
|
| 1105 |
+
"rstrip": false,
|
| 1106 |
+
"single_word": false,
|
| 1107 |
+
"special": false
|
| 1108 |
+
},
|
| 1109 |
+
"138": {
|
| 1110 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1111 |
+
"lstrip": false,
|
| 1112 |
+
"normalized": false,
|
| 1113 |
+
"rstrip": false,
|
| 1114 |
+
"single_word": false,
|
| 1115 |
+
"special": false
|
| 1116 |
+
},
|
| 1117 |
+
"139": {
|
| 1118 |
+
"content": "▁▁",
|
| 1119 |
+
"lstrip": false,
|
| 1120 |
+
"normalized": false,
|
| 1121 |
+
"rstrip": false,
|
| 1122 |
+
"single_word": false,
|
| 1123 |
+
"special": false
|
| 1124 |
+
},
|
| 1125 |
+
"140": {
|
| 1126 |
+
"content": "▁▁▁",
|
| 1127 |
+
"lstrip": false,
|
| 1128 |
+
"normalized": false,
|
| 1129 |
+
"rstrip": false,
|
| 1130 |
+
"single_word": false,
|
| 1131 |
+
"special": false
|
| 1132 |
+
},
|
| 1133 |
+
"141": {
|
| 1134 |
+
"content": "▁▁▁▁",
|
| 1135 |
+
"lstrip": false,
|
| 1136 |
+
"normalized": false,
|
| 1137 |
+
"rstrip": false,
|
| 1138 |
+
"single_word": false,
|
| 1139 |
+
"special": false
|
| 1140 |
+
},
|
| 1141 |
+
"142": {
|
| 1142 |
+
"content": "▁▁▁▁▁",
|
| 1143 |
+
"lstrip": false,
|
| 1144 |
+
"normalized": false,
|
| 1145 |
+
"rstrip": false,
|
| 1146 |
+
"single_word": false,
|
| 1147 |
+
"special": false
|
| 1148 |
+
},
|
| 1149 |
+
"143": {
|
| 1150 |
+
"content": "▁▁▁▁▁▁",
|
| 1151 |
+
"lstrip": false,
|
| 1152 |
+
"normalized": false,
|
| 1153 |
+
"rstrip": false,
|
| 1154 |
+
"single_word": false,
|
| 1155 |
+
"special": false
|
| 1156 |
+
},
|
| 1157 |
+
"144": {
|
| 1158 |
+
"content": "▁▁▁▁▁▁▁",
|
| 1159 |
+
"lstrip": false,
|
| 1160 |
+
"normalized": false,
|
| 1161 |
+
"rstrip": false,
|
| 1162 |
+
"single_word": false,
|
| 1163 |
+
"special": false
|
| 1164 |
+
},
|
| 1165 |
+
"145": {
|
| 1166 |
+
"content": "▁▁▁▁▁▁▁▁",
|
| 1167 |
+
"lstrip": false,
|
| 1168 |
+
"normalized": false,
|
| 1169 |
+
"rstrip": false,
|
| 1170 |
+
"single_word": false,
|
| 1171 |
+
"special": false
|
| 1172 |
+
},
|
| 1173 |
+
"146": {
|
| 1174 |
+
"content": "▁▁▁▁▁▁▁▁▁",
|
| 1175 |
+
"lstrip": false,
|
| 1176 |
+
"normalized": false,
|
| 1177 |
+
"rstrip": false,
|
| 1178 |
+
"single_word": false,
|
| 1179 |
+
"special": false
|
| 1180 |
+
},
|
| 1181 |
+
"147": {
|
| 1182 |
+
"content": "▁▁▁▁▁▁▁▁▁▁",
|
| 1183 |
+
"lstrip": false,
|
| 1184 |
+
"normalized": false,
|
| 1185 |
+
"rstrip": false,
|
| 1186 |
+
"single_word": false,
|
| 1187 |
+
"special": false
|
| 1188 |
+
},
|
| 1189 |
+
"148": {
|
| 1190 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁",
|
| 1191 |
+
"lstrip": false,
|
| 1192 |
+
"normalized": false,
|
| 1193 |
+
"rstrip": false,
|
| 1194 |
+
"single_word": false,
|
| 1195 |
+
"special": false
|
| 1196 |
+
},
|
| 1197 |
+
"149": {
|
| 1198 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1199 |
+
"lstrip": false,
|
| 1200 |
+
"normalized": false,
|
| 1201 |
+
"rstrip": false,
|
| 1202 |
+
"single_word": false,
|
| 1203 |
+
"special": false
|
| 1204 |
+
},
|
| 1205 |
+
"150": {
|
| 1206 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1207 |
+
"lstrip": false,
|
| 1208 |
+
"normalized": false,
|
| 1209 |
+
"rstrip": false,
|
| 1210 |
+
"single_word": false,
|
| 1211 |
+
"special": false
|
| 1212 |
+
},
|
| 1213 |
+
"151": {
|
| 1214 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1215 |
+
"lstrip": false,
|
| 1216 |
+
"normalized": false,
|
| 1217 |
+
"rstrip": false,
|
| 1218 |
+
"single_word": false,
|
| 1219 |
+
"special": false
|
| 1220 |
+
},
|
| 1221 |
+
"152": {
|
| 1222 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1223 |
+
"lstrip": false,
|
| 1224 |
+
"normalized": false,
|
| 1225 |
+
"rstrip": false,
|
| 1226 |
+
"single_word": false,
|
| 1227 |
+
"special": false
|
| 1228 |
+
},
|
| 1229 |
+
"153": {
|
| 1230 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1231 |
+
"lstrip": false,
|
| 1232 |
+
"normalized": false,
|
| 1233 |
+
"rstrip": false,
|
| 1234 |
+
"single_word": false,
|
| 1235 |
+
"special": false
|
| 1236 |
+
},
|
| 1237 |
+
"154": {
|
| 1238 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1239 |
+
"lstrip": false,
|
| 1240 |
+
"normalized": false,
|
| 1241 |
+
"rstrip": false,
|
| 1242 |
+
"single_word": false,
|
| 1243 |
+
"special": false
|
| 1244 |
+
},
|
| 1245 |
+
"155": {
|
| 1246 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1247 |
+
"lstrip": false,
|
| 1248 |
+
"normalized": false,
|
| 1249 |
+
"rstrip": false,
|
| 1250 |
+
"single_word": false,
|
| 1251 |
+
"special": false
|
| 1252 |
+
},
|
| 1253 |
+
"156": {
|
| 1254 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1255 |
+
"lstrip": false,
|
| 1256 |
+
"normalized": false,
|
| 1257 |
+
"rstrip": false,
|
| 1258 |
+
"single_word": false,
|
| 1259 |
+
"special": false
|
| 1260 |
+
},
|
| 1261 |
+
"157": {
|
| 1262 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1263 |
+
"lstrip": false,
|
| 1264 |
+
"normalized": false,
|
| 1265 |
+
"rstrip": false,
|
| 1266 |
+
"single_word": false,
|
| 1267 |
+
"special": false
|
| 1268 |
+
},
|
| 1269 |
+
"158": {
|
| 1270 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1271 |
+
"lstrip": false,
|
| 1272 |
+
"normalized": false,
|
| 1273 |
+
"rstrip": false,
|
| 1274 |
+
"single_word": false,
|
| 1275 |
+
"special": false
|
| 1276 |
+
},
|
| 1277 |
+
"159": {
|
| 1278 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1279 |
+
"lstrip": false,
|
| 1280 |
+
"normalized": false,
|
| 1281 |
+
"rstrip": false,
|
| 1282 |
+
"single_word": false,
|
| 1283 |
+
"special": false
|
| 1284 |
+
},
|
| 1285 |
+
"160": {
|
| 1286 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1287 |
+
"lstrip": false,
|
| 1288 |
+
"normalized": false,
|
| 1289 |
+
"rstrip": false,
|
| 1290 |
+
"single_word": false,
|
| 1291 |
+
"special": false
|
| 1292 |
+
},
|
| 1293 |
+
"161": {
|
| 1294 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1295 |
+
"lstrip": false,
|
| 1296 |
+
"normalized": false,
|
| 1297 |
+
"rstrip": false,
|
| 1298 |
+
"single_word": false,
|
| 1299 |
+
"special": false
|
| 1300 |
+
},
|
| 1301 |
+
"162": {
|
| 1302 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1303 |
+
"lstrip": false,
|
| 1304 |
+
"normalized": false,
|
| 1305 |
+
"rstrip": false,
|
| 1306 |
+
"single_word": false,
|
| 1307 |
+
"special": false
|
| 1308 |
+
},
|
| 1309 |
+
"163": {
|
| 1310 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1311 |
+
"lstrip": false,
|
| 1312 |
+
"normalized": false,
|
| 1313 |
+
"rstrip": false,
|
| 1314 |
+
"single_word": false,
|
| 1315 |
+
"special": false
|
| 1316 |
+
},
|
| 1317 |
+
"164": {
|
| 1318 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1319 |
+
"lstrip": false,
|
| 1320 |
+
"normalized": false,
|
| 1321 |
+
"rstrip": false,
|
| 1322 |
+
"single_word": false,
|
| 1323 |
+
"special": false
|
| 1324 |
+
},
|
| 1325 |
+
"165": {
|
| 1326 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1327 |
+
"lstrip": false,
|
| 1328 |
+
"normalized": false,
|
| 1329 |
+
"rstrip": false,
|
| 1330 |
+
"single_word": false,
|
| 1331 |
+
"special": false
|
| 1332 |
+
},
|
| 1333 |
+
"166": {
|
| 1334 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1335 |
+
"lstrip": false,
|
| 1336 |
+
"normalized": false,
|
| 1337 |
+
"rstrip": false,
|
| 1338 |
+
"single_word": false,
|
| 1339 |
+
"special": false
|
| 1340 |
+
},
|
| 1341 |
+
"167": {
|
| 1342 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1343 |
+
"lstrip": false,
|
| 1344 |
+
"normalized": false,
|
| 1345 |
+
"rstrip": false,
|
| 1346 |
+
"single_word": false,
|
| 1347 |
+
"special": false
|
| 1348 |
+
},
|
| 1349 |
+
"168": {
|
| 1350 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1351 |
+
"lstrip": false,
|
| 1352 |
+
"normalized": false,
|
| 1353 |
+
"rstrip": false,
|
| 1354 |
+
"single_word": false,
|
| 1355 |
+
"special": false
|
| 1356 |
+
},
|
| 1357 |
+
"169": {
|
| 1358 |
+
"content": "<table>",
|
| 1359 |
+
"lstrip": false,
|
| 1360 |
+
"normalized": false,
|
| 1361 |
+
"rstrip": false,
|
| 1362 |
+
"single_word": false,
|
| 1363 |
+
"special": false
|
| 1364 |
+
},
|
| 1365 |
+
"170": {
|
| 1366 |
+
"content": "<caption>",
|
| 1367 |
+
"lstrip": false,
|
| 1368 |
+
"normalized": false,
|
| 1369 |
+
"rstrip": false,
|
| 1370 |
+
"single_word": false,
|
| 1371 |
+
"special": false
|
| 1372 |
+
},
|
| 1373 |
+
"171": {
|
| 1374 |
+
"content": "<thead>",
|
| 1375 |
+
"lstrip": false,
|
| 1376 |
+
"normalized": false,
|
| 1377 |
+
"rstrip": false,
|
| 1378 |
+
"single_word": false,
|
| 1379 |
+
"special": false
|
| 1380 |
+
},
|
| 1381 |
+
"172": {
|
| 1382 |
+
"content": "<tbody>",
|
| 1383 |
+
"lstrip": false,
|
| 1384 |
+
"normalized": false,
|
| 1385 |
+
"rstrip": false,
|
| 1386 |
+
"single_word": false,
|
| 1387 |
+
"special": false
|
| 1388 |
+
},
|
| 1389 |
+
"173": {
|
| 1390 |
+
"content": "<tfoot>",
|
| 1391 |
+
"lstrip": false,
|
| 1392 |
+
"normalized": false,
|
| 1393 |
+
"rstrip": false,
|
| 1394 |
+
"single_word": false,
|
| 1395 |
+
"special": false
|
| 1396 |
+
},
|
| 1397 |
+
"174": {
|
| 1398 |
+
"content": "<tr>",
|
| 1399 |
+
"lstrip": false,
|
| 1400 |
+
"normalized": false,
|
| 1401 |
+
"rstrip": false,
|
| 1402 |
+
"single_word": false,
|
| 1403 |
+
"special": false
|
| 1404 |
+
},
|
| 1405 |
+
"175": {
|
| 1406 |
+
"content": "<th>",
|
| 1407 |
+
"lstrip": false,
|
| 1408 |
+
"normalized": false,
|
| 1409 |
+
"rstrip": false,
|
| 1410 |
+
"single_word": false,
|
| 1411 |
+
"special": false
|
| 1412 |
+
},
|
| 1413 |
+
"176": {
|
| 1414 |
+
"content": "<td>",
|
| 1415 |
+
"lstrip": false,
|
| 1416 |
+
"normalized": false,
|
| 1417 |
+
"rstrip": false,
|
| 1418 |
+
"single_word": false,
|
| 1419 |
+
"special": false
|
| 1420 |
+
},
|
| 1421 |
+
"177": {
|
| 1422 |
+
"content": "</table>",
|
| 1423 |
+
"lstrip": false,
|
| 1424 |
+
"normalized": false,
|
| 1425 |
+
"rstrip": false,
|
| 1426 |
+
"single_word": false,
|
| 1427 |
+
"special": false
|
| 1428 |
+
},
|
| 1429 |
+
"178": {
|
| 1430 |
+
"content": "</caption>",
|
| 1431 |
+
"lstrip": false,
|
| 1432 |
+
"normalized": false,
|
| 1433 |
+
"rstrip": false,
|
| 1434 |
+
"single_word": false,
|
| 1435 |
+
"special": false
|
| 1436 |
+
},
|
| 1437 |
+
"179": {
|
| 1438 |
+
"content": "</thead>",
|
| 1439 |
+
"lstrip": false,
|
| 1440 |
+
"normalized": false,
|
| 1441 |
+
"rstrip": false,
|
| 1442 |
+
"single_word": false,
|
| 1443 |
+
"special": false
|
| 1444 |
+
},
|
| 1445 |
+
"180": {
|
| 1446 |
+
"content": "</tbody>",
|
| 1447 |
+
"lstrip": false,
|
| 1448 |
+
"normalized": false,
|
| 1449 |
+
"rstrip": false,
|
| 1450 |
+
"single_word": false,
|
| 1451 |
+
"special": false
|
| 1452 |
+
},
|
| 1453 |
+
"181": {
|
| 1454 |
+
"content": "</tfoot>",
|
| 1455 |
+
"lstrip": false,
|
| 1456 |
+
"normalized": false,
|
| 1457 |
+
"rstrip": false,
|
| 1458 |
+
"single_word": false,
|
| 1459 |
+
"special": false
|
| 1460 |
+
},
|
| 1461 |
+
"182": {
|
| 1462 |
+
"content": "</tr>",
|
| 1463 |
+
"lstrip": false,
|
| 1464 |
+
"normalized": false,
|
| 1465 |
+
"rstrip": false,
|
| 1466 |
+
"single_word": false,
|
| 1467 |
+
"special": false
|
| 1468 |
+
},
|
| 1469 |
+
"183": {
|
| 1470 |
+
"content": "</th>",
|
| 1471 |
+
"lstrip": false,
|
| 1472 |
+
"normalized": false,
|
| 1473 |
+
"rstrip": false,
|
| 1474 |
+
"single_word": false,
|
| 1475 |
+
"special": false
|
| 1476 |
+
},
|
| 1477 |
+
"184": {
|
| 1478 |
+
"content": "</td>",
|
| 1479 |
+
"lstrip": false,
|
| 1480 |
+
"normalized": false,
|
| 1481 |
+
"rstrip": false,
|
| 1482 |
+
"single_word": false,
|
| 1483 |
+
"special": false
|
| 1484 |
+
},
|
| 1485 |
+
"185": {
|
| 1486 |
+
"content": "<h1>",
|
| 1487 |
+
"lstrip": false,
|
| 1488 |
+
"normalized": false,
|
| 1489 |
+
"rstrip": false,
|
| 1490 |
+
"single_word": false,
|
| 1491 |
+
"special": false
|
| 1492 |
+
},
|
| 1493 |
+
"186": {
|
| 1494 |
+
"content": "<h2>",
|
| 1495 |
+
"lstrip": false,
|
| 1496 |
+
"normalized": false,
|
| 1497 |
+
"rstrip": false,
|
| 1498 |
+
"single_word": false,
|
| 1499 |
+
"special": false
|
| 1500 |
+
},
|
| 1501 |
+
"187": {
|
| 1502 |
+
"content": "<h3>",
|
| 1503 |
+
"lstrip": false,
|
| 1504 |
+
"normalized": false,
|
| 1505 |
+
"rstrip": false,
|
| 1506 |
+
"single_word": false,
|
| 1507 |
+
"special": false
|
| 1508 |
+
},
|
| 1509 |
+
"188": {
|
| 1510 |
+
"content": "<h4>",
|
| 1511 |
+
"lstrip": false,
|
| 1512 |
+
"normalized": false,
|
| 1513 |
+
"rstrip": false,
|
| 1514 |
+
"single_word": false,
|
| 1515 |
+
"special": false
|
| 1516 |
+
},
|
| 1517 |
+
"189": {
|
| 1518 |
+
"content": "<h5>",
|
| 1519 |
+
"lstrip": false,
|
| 1520 |
+
"normalized": false,
|
| 1521 |
+
"rstrip": false,
|
| 1522 |
+
"single_word": false,
|
| 1523 |
+
"special": false
|
| 1524 |
+
},
|
| 1525 |
+
"190": {
|
| 1526 |
+
"content": "<h6>",
|
| 1527 |
+
"lstrip": false,
|
| 1528 |
+
"normalized": false,
|
| 1529 |
+
"rstrip": false,
|
| 1530 |
+
"single_word": false,
|
| 1531 |
+
"special": false
|
| 1532 |
+
},
|
| 1533 |
+
"191": {
|
| 1534 |
+
"content": "<blockquote>",
|
| 1535 |
+
"lstrip": false,
|
| 1536 |
+
"normalized": false,
|
| 1537 |
+
"rstrip": false,
|
| 1538 |
+
"single_word": false,
|
| 1539 |
+
"special": false
|
| 1540 |
+
},
|
| 1541 |
+
"192": {
|
| 1542 |
+
"content": "</h1>",
|
| 1543 |
+
"lstrip": false,
|
| 1544 |
+
"normalized": false,
|
| 1545 |
+
"rstrip": false,
|
| 1546 |
+
"single_word": false,
|
| 1547 |
+
"special": false
|
| 1548 |
+
},
|
| 1549 |
+
"193": {
|
| 1550 |
+
"content": "</h2>",
|
| 1551 |
+
"lstrip": false,
|
| 1552 |
+
"normalized": false,
|
| 1553 |
+
"rstrip": false,
|
| 1554 |
+
"single_word": false,
|
| 1555 |
+
"special": false
|
| 1556 |
+
},
|
| 1557 |
+
"194": {
|
| 1558 |
+
"content": "</h3>",
|
| 1559 |
+
"lstrip": false,
|
| 1560 |
+
"normalized": false,
|
| 1561 |
+
"rstrip": false,
|
| 1562 |
+
"single_word": false,
|
| 1563 |
+
"special": false
|
| 1564 |
+
},
|
| 1565 |
+
"195": {
|
| 1566 |
+
"content": "</h4>",
|
| 1567 |
+
"lstrip": false,
|
| 1568 |
+
"normalized": false,
|
| 1569 |
+
"rstrip": false,
|
| 1570 |
+
"single_word": false,
|
| 1571 |
+
"special": false
|
| 1572 |
+
},
|
| 1573 |
+
"196": {
|
| 1574 |
+
"content": "</h5>",
|
| 1575 |
+
"lstrip": false,
|
| 1576 |
+
"normalized": false,
|
| 1577 |
+
"rstrip": false,
|
| 1578 |
+
"single_word": false,
|
| 1579 |
+
"special": false
|
| 1580 |
+
},
|
| 1581 |
+
"197": {
|
| 1582 |
+
"content": "</h6>",
|
| 1583 |
+
"lstrip": false,
|
| 1584 |
+
"normalized": false,
|
| 1585 |
+
"rstrip": false,
|
| 1586 |
+
"single_word": false,
|
| 1587 |
+
"special": false
|
| 1588 |
+
},
|
| 1589 |
+
"198": {
|
| 1590 |
+
"content": "</blockquote>",
|
| 1591 |
+
"lstrip": false,
|
| 1592 |
+
"normalized": false,
|
| 1593 |
+
"rstrip": false,
|
| 1594 |
+
"single_word": false,
|
| 1595 |
+
"special": false
|
| 1596 |
+
},
|
| 1597 |
+
"199": {
|
| 1598 |
+
"content": "<strong>",
|
| 1599 |
+
"lstrip": false,
|
| 1600 |
+
"normalized": false,
|
| 1601 |
+
"rstrip": false,
|
| 1602 |
+
"single_word": false,
|
| 1603 |
+
"special": false
|
| 1604 |
+
},
|
| 1605 |
+
"200": {
|
| 1606 |
+
"content": "<em>",
|
| 1607 |
+
"lstrip": false,
|
| 1608 |
+
"normalized": false,
|
| 1609 |
+
"rstrip": false,
|
| 1610 |
+
"single_word": false,
|
| 1611 |
+
"special": false
|
| 1612 |
+
},
|
| 1613 |
+
"201": {
|
| 1614 |
+
"content": "<b>",
|
| 1615 |
+
"lstrip": false,
|
| 1616 |
+
"normalized": false,
|
| 1617 |
+
"rstrip": false,
|
| 1618 |
+
"single_word": false,
|
| 1619 |
+
"special": false
|
| 1620 |
+
},
|
| 1621 |
+
"202": {
|
| 1622 |
+
"content": "<i>",
|
| 1623 |
+
"lstrip": false,
|
| 1624 |
+
"normalized": false,
|
| 1625 |
+
"rstrip": false,
|
| 1626 |
+
"single_word": false,
|
| 1627 |
+
"special": false
|
| 1628 |
+
},
|
| 1629 |
+
"203": {
|
| 1630 |
+
"content": "<u>",
|
| 1631 |
+
"lstrip": false,
|
| 1632 |
+
"normalized": false,
|
| 1633 |
+
"rstrip": false,
|
| 1634 |
+
"single_word": false,
|
| 1635 |
+
"special": false
|
| 1636 |
+
},
|
| 1637 |
+
"204": {
|
| 1638 |
+
"content": "<s>",
|
| 1639 |
+
"lstrip": false,
|
| 1640 |
+
"normalized": false,
|
| 1641 |
+
"rstrip": false,
|
| 1642 |
+
"single_word": false,
|
| 1643 |
+
"special": false
|
| 1644 |
+
},
|
| 1645 |
+
"205": {
|
| 1646 |
+
"content": "<sub>",
|
| 1647 |
+
"lstrip": false,
|
| 1648 |
+
"normalized": false,
|
| 1649 |
+
"rstrip": false,
|
| 1650 |
+
"single_word": false,
|
| 1651 |
+
"special": false
|
| 1652 |
+
},
|
| 1653 |
+
"206": {
|
| 1654 |
+
"content": "<sup>",
|
| 1655 |
+
"lstrip": false,
|
| 1656 |
+
"normalized": false,
|
| 1657 |
+
"rstrip": false,
|
| 1658 |
+
"single_word": false,
|
| 1659 |
+
"special": false
|
| 1660 |
+
},
|
| 1661 |
+
"207": {
|
| 1662 |
+
"content": "<code>",
|
| 1663 |
+
"lstrip": false,
|
| 1664 |
+
"normalized": false,
|
| 1665 |
+
"rstrip": false,
|
| 1666 |
+
"single_word": false,
|
| 1667 |
+
"special": false
|
| 1668 |
+
},
|
| 1669 |
+
"208": {
|
| 1670 |
+
"content": "</strong>",
|
| 1671 |
+
"lstrip": false,
|
| 1672 |
+
"normalized": false,
|
| 1673 |
+
"rstrip": false,
|
| 1674 |
+
"single_word": false,
|
| 1675 |
+
"special": false
|
| 1676 |
+
},
|
| 1677 |
+
"209": {
|
| 1678 |
+
"content": "</em>",
|
| 1679 |
+
"lstrip": false,
|
| 1680 |
+
"normalized": false,
|
| 1681 |
+
"rstrip": false,
|
| 1682 |
+
"single_word": false,
|
| 1683 |
+
"special": false
|
| 1684 |
+
},
|
| 1685 |
+
"210": {
|
| 1686 |
+
"content": "</b>",
|
| 1687 |
+
"lstrip": false,
|
| 1688 |
+
"normalized": false,
|
| 1689 |
+
"rstrip": false,
|
| 1690 |
+
"single_word": false,
|
| 1691 |
+
"special": false
|
| 1692 |
+
},
|
| 1693 |
+
"211": {
|
| 1694 |
+
"content": "</i>",
|
| 1695 |
+
"lstrip": false,
|
| 1696 |
+
"normalized": false,
|
| 1697 |
+
"rstrip": false,
|
| 1698 |
+
"single_word": false,
|
| 1699 |
+
"special": false
|
| 1700 |
+
},
|
| 1701 |
+
"212": {
|
| 1702 |
+
"content": "</u>",
|
| 1703 |
+
"lstrip": false,
|
| 1704 |
+
"normalized": false,
|
| 1705 |
+
"rstrip": false,
|
| 1706 |
+
"single_word": false,
|
| 1707 |
+
"special": false
|
| 1708 |
+
},
|
| 1709 |
+
"213": {
|
| 1710 |
+
"content": "</s>",
|
| 1711 |
+
"lstrip": false,
|
| 1712 |
+
"normalized": false,
|
| 1713 |
+
"rstrip": false,
|
| 1714 |
+
"single_word": false,
|
| 1715 |
+
"special": false
|
| 1716 |
+
},
|
| 1717 |
+
"214": {
|
| 1718 |
+
"content": "</sub>",
|
| 1719 |
+
"lstrip": false,
|
| 1720 |
+
"normalized": false,
|
| 1721 |
+
"rstrip": false,
|
| 1722 |
+
"single_word": false,
|
| 1723 |
+
"special": false
|
| 1724 |
+
},
|
| 1725 |
+
"215": {
|
| 1726 |
+
"content": "</sup>",
|
| 1727 |
+
"lstrip": false,
|
| 1728 |
+
"normalized": false,
|
| 1729 |
+
"rstrip": false,
|
| 1730 |
+
"single_word": false,
|
| 1731 |
+
"special": false
|
| 1732 |
+
},
|
| 1733 |
+
"216": {
|
| 1734 |
+
"content": "</code>",
|
| 1735 |
+
"lstrip": false,
|
| 1736 |
+
"normalized": false,
|
| 1737 |
+
"rstrip": false,
|
| 1738 |
+
"single_word": false,
|
| 1739 |
+
"special": false
|
| 1740 |
+
},
|
| 1741 |
+
"255968": {
|
| 1742 |
+
"content": "[toxicity=0]",
|
| 1743 |
+
"lstrip": false,
|
| 1744 |
+
"normalized": false,
|
| 1745 |
+
"rstrip": false,
|
| 1746 |
+
"single_word": false,
|
| 1747 |
+
"special": false
|
| 1748 |
+
},
|
| 1749 |
+
"255969": {
|
| 1750 |
+
"content": "\t\t",
|
| 1751 |
+
"lstrip": false,
|
| 1752 |
+
"normalized": false,
|
| 1753 |
+
"rstrip": false,
|
| 1754 |
+
"single_word": false,
|
| 1755 |
+
"special": false
|
| 1756 |
+
},
|
| 1757 |
+
"255970": {
|
| 1758 |
+
"content": "\t\t\t",
|
| 1759 |
+
"lstrip": false,
|
| 1760 |
+
"normalized": false,
|
| 1761 |
+
"rstrip": false,
|
| 1762 |
+
"single_word": false,
|
| 1763 |
+
"special": false
|
| 1764 |
+
},
|
| 1765 |
+
"255971": {
|
| 1766 |
+
"content": "\t\t\t\t",
|
| 1767 |
+
"lstrip": false,
|
| 1768 |
+
"normalized": false,
|
| 1769 |
+
"rstrip": false,
|
| 1770 |
+
"single_word": false,
|
| 1771 |
+
"special": false
|
| 1772 |
+
},
|
| 1773 |
+
"255972": {
|
| 1774 |
+
"content": "\t\t\t\t\t",
|
| 1775 |
+
"lstrip": false,
|
| 1776 |
+
"normalized": false,
|
| 1777 |
+
"rstrip": false,
|
| 1778 |
+
"single_word": false,
|
| 1779 |
+
"special": false
|
| 1780 |
+
},
|
| 1781 |
+
"255973": {
|
| 1782 |
+
"content": "\t\t\t\t\t\t",
|
| 1783 |
+
"lstrip": false,
|
| 1784 |
+
"normalized": false,
|
| 1785 |
+
"rstrip": false,
|
| 1786 |
+
"single_word": false,
|
| 1787 |
+
"special": false
|
| 1788 |
+
},
|
| 1789 |
+
"255974": {
|
| 1790 |
+
"content": "\t\t\t\t\t\t\t",
|
| 1791 |
+
"lstrip": false,
|
| 1792 |
+
"normalized": false,
|
| 1793 |
+
"rstrip": false,
|
| 1794 |
+
"single_word": false,
|
| 1795 |
+
"special": false
|
| 1796 |
+
},
|
| 1797 |
+
"255975": {
|
| 1798 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 1799 |
+
"lstrip": false,
|
| 1800 |
+
"normalized": false,
|
| 1801 |
+
"rstrip": false,
|
| 1802 |
+
"single_word": false,
|
| 1803 |
+
"special": false
|
| 1804 |
+
},
|
| 1805 |
+
"255976": {
|
| 1806 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 1807 |
+
"lstrip": false,
|
| 1808 |
+
"normalized": false,
|
| 1809 |
+
"rstrip": false,
|
| 1810 |
+
"single_word": false,
|
| 1811 |
+
"special": false
|
| 1812 |
+
},
|
| 1813 |
+
"255977": {
|
| 1814 |
+
"content": "\t\t\t\t\t\t\t\t\t\t",
|
| 1815 |
+
"lstrip": false,
|
| 1816 |
+
"normalized": false,
|
| 1817 |
+
"rstrip": false,
|
| 1818 |
+
"single_word": false,
|
| 1819 |
+
"special": false
|
| 1820 |
+
},
|
| 1821 |
+
"255978": {
|
| 1822 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t",
|
| 1823 |
+
"lstrip": false,
|
| 1824 |
+
"normalized": false,
|
| 1825 |
+
"rstrip": false,
|
| 1826 |
+
"single_word": false,
|
| 1827 |
+
"special": false
|
| 1828 |
+
},
|
| 1829 |
+
"255979": {
|
| 1830 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1831 |
+
"lstrip": false,
|
| 1832 |
+
"normalized": false,
|
| 1833 |
+
"rstrip": false,
|
| 1834 |
+
"single_word": false,
|
| 1835 |
+
"special": false
|
| 1836 |
+
},
|
| 1837 |
+
"255980": {
|
| 1838 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1839 |
+
"lstrip": false,
|
| 1840 |
+
"normalized": false,
|
| 1841 |
+
"rstrip": false,
|
| 1842 |
+
"single_word": false,
|
| 1843 |
+
"special": false
|
| 1844 |
+
},
|
| 1845 |
+
"255981": {
|
| 1846 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1847 |
+
"lstrip": false,
|
| 1848 |
+
"normalized": false,
|
| 1849 |
+
"rstrip": false,
|
| 1850 |
+
"single_word": false,
|
| 1851 |
+
"special": false
|
| 1852 |
+
},
|
| 1853 |
+
"255982": {
|
| 1854 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1855 |
+
"lstrip": false,
|
| 1856 |
+
"normalized": false,
|
| 1857 |
+
"rstrip": false,
|
| 1858 |
+
"single_word": false,
|
| 1859 |
+
"special": false
|
| 1860 |
+
},
|
| 1861 |
+
"255983": {
|
| 1862 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1863 |
+
"lstrip": false,
|
| 1864 |
+
"normalized": false,
|
| 1865 |
+
"rstrip": false,
|
| 1866 |
+
"single_word": false,
|
| 1867 |
+
"special": false
|
| 1868 |
+
},
|
| 1869 |
+
"255984": {
|
| 1870 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1871 |
+
"lstrip": false,
|
| 1872 |
+
"normalized": false,
|
| 1873 |
+
"rstrip": false,
|
| 1874 |
+
"single_word": false,
|
| 1875 |
+
"special": false
|
| 1876 |
+
},
|
| 1877 |
+
"255985": {
|
| 1878 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1879 |
+
"lstrip": false,
|
| 1880 |
+
"normalized": false,
|
| 1881 |
+
"rstrip": false,
|
| 1882 |
+
"single_word": false,
|
| 1883 |
+
"special": false
|
| 1884 |
+
},
|
| 1885 |
+
"255986": {
|
| 1886 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1887 |
+
"lstrip": false,
|
| 1888 |
+
"normalized": false,
|
| 1889 |
+
"rstrip": false,
|
| 1890 |
+
"single_word": false,
|
| 1891 |
+
"special": false
|
| 1892 |
+
},
|
| 1893 |
+
"255987": {
|
| 1894 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1895 |
+
"lstrip": false,
|
| 1896 |
+
"normalized": false,
|
| 1897 |
+
"rstrip": false,
|
| 1898 |
+
"single_word": false,
|
| 1899 |
+
"special": false
|
| 1900 |
+
},
|
| 1901 |
+
"255988": {
|
| 1902 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1903 |
+
"lstrip": false,
|
| 1904 |
+
"normalized": false,
|
| 1905 |
+
"rstrip": false,
|
| 1906 |
+
"single_word": false,
|
| 1907 |
+
"special": false
|
| 1908 |
+
},
|
| 1909 |
+
"255989": {
|
| 1910 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1911 |
+
"lstrip": false,
|
| 1912 |
+
"normalized": false,
|
| 1913 |
+
"rstrip": false,
|
| 1914 |
+
"single_word": false,
|
| 1915 |
+
"special": false
|
| 1916 |
+
},
|
| 1917 |
+
"255990": {
|
| 1918 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1919 |
+
"lstrip": false,
|
| 1920 |
+
"normalized": false,
|
| 1921 |
+
"rstrip": false,
|
| 1922 |
+
"single_word": false,
|
| 1923 |
+
"special": false
|
| 1924 |
+
},
|
| 1925 |
+
"255991": {
|
| 1926 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1927 |
+
"lstrip": false,
|
| 1928 |
+
"normalized": false,
|
| 1929 |
+
"rstrip": false,
|
| 1930 |
+
"single_word": false,
|
| 1931 |
+
"special": false
|
| 1932 |
+
},
|
| 1933 |
+
"255992": {
|
| 1934 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1935 |
+
"lstrip": false,
|
| 1936 |
+
"normalized": false,
|
| 1937 |
+
"rstrip": false,
|
| 1938 |
+
"single_word": false,
|
| 1939 |
+
"special": false
|
| 1940 |
+
},
|
| 1941 |
+
"255993": {
|
| 1942 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1943 |
+
"lstrip": false,
|
| 1944 |
+
"normalized": false,
|
| 1945 |
+
"rstrip": false,
|
| 1946 |
+
"single_word": false,
|
| 1947 |
+
"special": false
|
| 1948 |
+
},
|
| 1949 |
+
"255994": {
|
| 1950 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1951 |
+
"lstrip": false,
|
| 1952 |
+
"normalized": false,
|
| 1953 |
+
"rstrip": false,
|
| 1954 |
+
"single_word": false,
|
| 1955 |
+
"special": false
|
| 1956 |
+
},
|
| 1957 |
+
"255995": {
|
| 1958 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1959 |
+
"lstrip": false,
|
| 1960 |
+
"normalized": false,
|
| 1961 |
+
"rstrip": false,
|
| 1962 |
+
"single_word": false,
|
| 1963 |
+
"special": false
|
| 1964 |
+
},
|
| 1965 |
+
"255996": {
|
| 1966 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1967 |
+
"lstrip": false,
|
| 1968 |
+
"normalized": false,
|
| 1969 |
+
"rstrip": false,
|
| 1970 |
+
"single_word": false,
|
| 1971 |
+
"special": false
|
| 1972 |
+
},
|
| 1973 |
+
"255997": {
|
| 1974 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1975 |
+
"lstrip": false,
|
| 1976 |
+
"normalized": false,
|
| 1977 |
+
"rstrip": false,
|
| 1978 |
+
"single_word": false,
|
| 1979 |
+
"special": false
|
| 1980 |
+
},
|
| 1981 |
+
"255998": {
|
| 1982 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1983 |
+
"lstrip": false,
|
| 1984 |
+
"normalized": false,
|
| 1985 |
+
"rstrip": false,
|
| 1986 |
+
"single_word": false,
|
| 1987 |
+
"special": false
|
| 1988 |
+
},
|
| 1989 |
+
"255999": {
|
| 1990 |
+
"content": "<SpeechHere>",
|
| 1991 |
+
"lstrip": false,
|
| 1992 |
+
"normalized": false,
|
| 1993 |
+
"rstrip": false,
|
| 1994 |
+
"single_word": false,
|
| 1995 |
+
"special": false
|
| 1996 |
+
}
|
| 1997 |
+
},
|
| 1998 |
+
"additional_special_tokens": [
|
| 1999 |
+
"<start_of_turn>",
|
| 2000 |
+
"<end_of_turn>"
|
| 2001 |
+
],
|
| 2002 |
+
"auto_map": {
|
| 2003 |
+
"AutoProcessor": "processing_meralion3.MERaLiON3Processor"
|
| 2004 |
+
},
|
| 2005 |
+
"bos_token": "<bos>",
|
| 2006 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
| 2007 |
+
"clean_up_tokenization_spaces": false,
|
| 2008 |
+
"eos_token": "<eos>",
|
| 2009 |
+
"extra_special_tokens": {},
|
| 2010 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 2011 |
+
"pad_token": "<pad>",
|
| 2012 |
+
"padding_side": "left",
|
| 2013 |
+
"processor_class": "MERaLiON3Processor",
|
| 2014 |
+
"sp_model_kwargs": {},
|
| 2015 |
+
"spaces_between_special_tokens": false,
|
| 2016 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 2017 |
+
"unk_token": "<unk>",
|
| 2018 |
+
"use_default_system_prompt": false
|
| 2019 |
+
}
|