llm-training-playground

Here are some of my notes for Fine-Tuning LLM with Hugging Face's Library (PEFT, SFT, PPO, etc.).

Finetuning Notebook Table

Notebook/file Title	Description	Model	GPU
Finetuning a Mistral 7B Model with LoRA	Training with custom dataset	Mistral-7B	RTX 4090
Fine-tune Llama-3 with SFT	Training with custom dataset	Llama 3	A6000