Fine-tuning
- Model Fine-tuning Process
- LoRA
- Llama-factory
- Base Open-Source Models
- MoE: Mixture of Experts Model
- RLHF: Reinforcement Learning from Human Feedback
About 7 min
Best Practices for Optimizing LLMs (Prompt Engineering, RAG and Fine-tuning)
- The Optimization Strategies
- Typical Optimization Pipeline
- Comparison of Optimisation Approaches
- OpenAI RAG Use Case
About 5 min