LLM_learner

Learning how to use, fine-tune and build with LLMs

Resources

LLMs

• [1hr Talk] Intro to Large Language Models
• A Hackers' Guide to Language Models

Fine-Tuning

• Finetuning open-source LLMshttps://www.youtube.com/watch?v=gs-IDg-FoIQ
• How to fine-tune Mistral 7b on your datahttps://www.youtube.com/watch?v=kmkcNVvEz-k
• Fine-Tuning your own Llama2https://www.youtube.com/watch?v=Pb_RGAl75VE&t=14s
• Webinar: How to Fine-Tune LLMs with QLoRA
• Fine-tuning Large Language Models (LLMs) | w/ Example Code

Lora

• What is LoRA? Low-Rank Adaptation for finetuning LLMs EXPLAINEDhttps://www.youtube.com/watch?v=KEv-F5UkhxU
• Low-rank Adaptation: LoRA Fine-tuning & QLoRA Explained In-Depthhttps://www.youtube.com/watch?v=t1caDsMzWBk&pp=ygUObG9yYSBhbmQgcWxvcmE%3D
• LoRA explained (and a bit about precision and quantization)https://www.youtube.com/watch?v=t509sv5MT0w&t=18s&pp=ygUObG9yYSBhbmQgcWxvcmE%3D
• Fine-Tune Large LLMs with QLoRA (Free Colab Tutorial)https://www.youtube.com/watch?v=NRVaRXDoI3g

Quantization

• Understanding 4bit Quantization: QLoRA explained (w/ Colab)https://www.youtube.com/watch?v=TPcXVJ1VSRI
• Understanding: AI Model Quantization, GGML vs GPTQ!
• AWQ for LLM Quantization
• How to Quantize an LLM with GGUF or AWQ
• New Tutorial on LLM Quantization w/ QLoRA, GPTQ and Llamacpp, LLama 2

PEFT

• PEFT LoRA Explained in Detail - Fine-Tune your LLM on your local GPUhttps://www.youtube.com/watch?v=YVU5wAA6Txo
• Fine-tuning LLMs with PEFT and LoRAhttps://www.youtube.com/watch?v=Us5ZFp16PaU
• Efficient Large Language Model training with LoRA and Hugging Face PEFThttps://www.youtube.com/watch?v=YKCtbIJC3kQ
• EMNLP 2022 Tutorial - "Modular and Parameter-Efficient Fine-Tuning for NLP Models"https://www.youtube.com/watch?v=KoOlcX3XLd4

DDPO / TRL

• Finetune Stable Diffusion Models with DDPO via TRLhttps://huggingface.co/blog/trl-ddpo
• Non-engineers guide: Train a LLaMA 2 chatbothttps://huggingface.co/blog/Llama2-for-non-engineers