Customizing LLMs: A Guide to local Fine-Tuning...
summary
Shows how to perform local fine-tuning of open-source LLMs (examples: Mixtral-8x22B-v0.1, Mistral-7B, Bloom-7B) to improve answer quality and specialize models for a domain. Explains why local fine-tuning matters for privacy, and demonstrates a step-by-step Python-based workflow using external libraries to implement fine-tuning on your own data.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 3:34Spanish data and models
- 8:22Project structure
- 13:07Model and hardware selection
- 15:47Fine-tuning techniques
- 19:13Local solutions and limits
- 21:19Technical steps
- 27:12Training and evaluation
- 30:11Conclusion
related talks
29mLocal LLM fine-tuning: a practical example
43mCreating Your Own Copy with a Fine-Tuned LLM
29mCustomizing and Evaluating LLMs, an Ops Perspective
09mTailoring Llama for Your Needs: Fine-Tuning & Evaluation
21mFrom Data to Precision: Fine-Tuning LLMs for Proprietary Query Languages
25mFinetuning Large Language Models (LLMs) for Security Log Detections
50mPimp My Llama - How to Customize LLMs for Your Business Case
40mInstructLab: Applying Open Source Methods to Building and Trai...