chuvash-ai/LFM3-1.7B-chv-llm-v1-GGUF
Text Generation • 2B • Updated • 291
None defined yet.
Chuvash (чӑваш чӗлхи) is a Turkic language of the Volga region with under a million speakers — too small for big AI companies to care, too important for its community to lose. We adapt open multilingual LLMs to Chuvash with continued pre-training and supervised fine-tuning, and release all data and models openly.
| Dataset | Size | Description |
|---|---|---|
| chuvash-ru-parallel | 1,459,170 pairs | Largest public Chuvash–Russian parallel corpus (CC0) |
| chuvash-en-parallel | 187,531 pairs | Largest public Chuvash–English parallel corpus (CC0) |
LFM3-1.7B-chv — Chuvash-adapted translation model family, released here with GGUF quants. The full fine-tune v2 is out now — our flagship.
| Model | ru → chv | chv → ru |
|---|---|---|
| MarianMT baseline | 23.3 | — |
| LFM3-1.7B-chv v1 (pilot, 2.6% of data) | 33.9 | 34.1 |
| LFM3-1.7B-chv v2 (full FT, all data) | 34.9 | 35.1 |
Founder: @efi-team