This repository groups a few notebooks I have used for teaching !
- Instruction Fine-tuning a SLM (Part 1)
- Base vs Instruct/Chat models
- LoRA Adapters
- Unsloth
- Quantization
- Chat templating and data preparation
- SFTTrainers
- Going further: Preparing your own finetuning dataset through synthetic data generation.
- Largely based on Unsloth AI resources
- Retrieval Augmented Generation with Vision Language Models (Part 2)
- Vision Language Models (Qwen2-VL)
- ColPali
- RAG
- API calls
Enjoy !