Kowalski-V3.1 — это дообученная Qwen3-4B на ~110 тысячах примеров. Я прокачал её в логике, математике, а также в коде. В неё добавлен блок с CoT. Модель была обучена методом Full Supervised Fine-Tuning (SFT).
Kowalski-V3.1 is a fine-tuned Qwen3-4B trained on ~110k examples. I upgraded its logic, math, and coding skills. It features a block with CoT. The model was trained using Full Supervised Fine-Tuning (SFT).
Have the files? Submit a torrent.
Submit a torrent →Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo ChikenBoy/Kowalski-V3.1 ./model-folder