by TYH-labs · Claude Skill · ★ 235
unsloth-buddy /unsloth-buddy I have 500 customer support Q&As and want to fine-tune a summarization model. I only have a MacBook Air. <img src="https://img.shields.io/badge/Try%20It-1%20minute-black?style=for-the-badge" alt="Tr
| Stars | 235 |
| Forks | 13 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 57.098/100 |
| Last Updated | 2026-05-07 |
| Created | 2026-03-15 |
| Platforms | claude-code, cli, gemini, python |
| Est. Tokens | ~199k |
Explore other popular claude skill tools:
unsloth-buddy is Zero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA · TRL+MPS/MLX on Apple Silicon. Automates env setup, LoRA training (SFT, DPO, GRPO, vision), post-hoc. It is categorized as a Claude Skill with 235 GitHub stars.
unsloth-buddy is primarily written in Python. It covers topics such as apple-silicon, claude-code, dpo.
You can find installation instructions and usage details in the unsloth-buddy GitHub repository at github.com/TYH-labs/unsloth-buddy. The project has 235 stars and 13 forks, indicating an active community.
unsloth-buddy is released under the MIT license, making it free to use and modify according to the license terms.