marco-jeffrey/awesome-llm-resources

a collection of resources around LLMs, aggregated for the workshop "Mastering LLMs: End-to-End Fine-Tuning and Deployment" by Dan Becker and Hamel Husain"

Awesome LLM resources

Contents

• Foundations
• Fine-Tuning
• RAG
• Axolotl
• Papers
• Multi-Modality
• Deployment
• Papers
• Miscellaneous

Foundations

Algorithms

Basics

• 3Blue1Brown Whatis GPT
• fastai's legendary DL course

Lecture series

• Umar's awesome DL channel

Models

• Llama 3 from scratch notebook

Fine-Tuning

Datasets

• Hamel blog data cleaning

Efficient training

Evals

• Hamel blog LLM evals
• LLM eval
• Evals blog post by Jason Way

Guides

• Moondream fine tune
• Lora instruction fine tuning
• Machine learning engineering for LLMs book
• When to finetune by OpenAI
• One year LLMs to production learnings

Monitoring

• Observability for LLMs

Output structuring

• LLM function Calling
• Blog on function calling
• Hermes function calling

Prompting

• DSPY
• Prompting by Anthropic
• Hamel blog prompting
• Prompt injection blog

Tokenization

• Hamel blog tokenizers

War stories

RAG

Guides

Links

• Stanford CS25- Retrieval Augmented Language Modeling

Projects

• cohere RAG toolkit

Axolotl

Guides

Projects

Setup

Papers

Fine tuning

• Finetuning on new knowledge
• DPO paper

General

Miscellaneous

• Extending context length of llama-3 by 10x

Models

• Vision Language models intro

RAG

• RAFT paper (RAG)

Safety

• The Instruction Hierarchy - LLM safety
• Harmlessness from AI Feedback

Multi-Modality

Guides

Projects

• Intern-VL open source multi model GPT

Deployment

APIs

Deployment

• Text-Generation-Inference(TGI)

• TensorRT-LLM/FastTransformer

• [vLLM/PageAttention/Continuous Batching](vLLM/PageAttention/Continuous Batching)

Guides

Papers

Fine tuning

• Finetuning on new knowledge
• DPO paper

General

Miscellaneous

• Extending context length of llama-3 by 10x

Models

• Vision Language models intro

RAG

• RAFT paper (RAG)

Safety

• The Instruction Hierarchy - LLM safety
• Harmlessness from AI Feedback

Miscellaneous

Links

• Anthropic's transformer-circuits blog
• Model comparison overview
• Hackers guide to LLM by @fastai

Podcasts

• Latent Space podcast with Jeremy

Interesting projects

• render ui with llm
• Langhain - Langsmith