Huggingface Fine-tuning

Contents

1. Transformer Fine-tuning

2. PEFT: Fine-tuning Basic

3. PEFT: Fine-tuning with QLoRA

4. PEFT: Fine-tuning Phi-2 with QLoRA

5. Axoltl Fine-tning with QLoRA

6. TRL: RLHF Alignment Fine-tuning

7. TRL: DPO Fine-tuning with Phi-3-4k-instruct

8. TRL: ORPO Fine-tuning with Llama3-8B

9. Convert GGUF gemma-2b with llama.cpp

10. Apple Silicon Fine-tuning Gemma-2B with MLX

11. LLM Mergekit

---

References:

• Huggingface 공식 문서: https://huggingface.co/docs

• Toward Data Science: https://towardsdatascience.com

• DeepLearning.ai 튜토리얼: https://www.deeplearning.ai/short-courses/

• mlabonee Blog: https://mlabonne.github.io/blog/

• Mergekit github: https://github.com/arcee-ai/mergekit

• Alex Ishida github: https://github.com/alexweberk

• Llama.cpp github: https://github.com/ggerganov/llama.cpp

• Axotle github: https://github.com/OpenAccess-AI-Collective/axolotl