ceos/unsloth

Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models. https://unsloth.ai/docs

agent deepseek fine-tuning gemma gemma3 gpt-oss llama llama3 llm llms mistral openai qwen reinforcement-learning self-hosted text-to-speech tts ui unsloth

Find a file

Roland Tannous 396b8fb9a4 Merge pull request #8 from unslothai/feature/frontendui-export-page-client-rebased feat: Add export page, HF model/dataset search, PDF/DOCX extraction logic, modern AUI API, and code cleanup		2026-02-02 19:55:54 +04:00
studio	refactor: update quantization options in export constants, remove unused entries, and add F32 option	2026-02-02 16:49:07 +01:00
.gitignore	refactor: format and clean up imports, hooks, and UI components for consistent structure and readability across models and datasets sections	2026-02-02 12:51:04 +01:00
__init__.py	git repo skeleton structure	2026-01-31 08:27:01 +00:00
CLAUDE.md	feat: add DOCX attachment support using `mammoth`, extend attachment handling to process and extract text from DOCX files	2026-02-02 16:33:10 +01:00
README.md	first commit	2026-01-27 21:19:48 +04:00

new-ui-prototype