This repository is a comprehensive collection of resources covering the latest advancements in Natural Language Processing (NLP), Large Language Models (LLMs), and cutting-edge techniques for training, fine-tuning, and deploying AI systems.
- Stanford CS336 Language Modeling from Scratch
- Yann Dubois: Scalable Evaluation of Large Language Models - video
- Stanford CS229 I Machine Learning I Building Large Language Models - video
Optimizing the finetuning process of large language models by reducing the number of parameters that need to be updated during training.
- Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey - Covers algorithmic design, computational efficiency, applications, and system implementation
- Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies - Latest comprehensive survey covering 100+ research articles from 2019-2024
- Understanding Parameter-Efficient Finetuning of Large Language Models: From Prefix Tuning to LLaMA-Adapters
- Parameter-Efficient LLM Finetuning With Low-Rank Adaptation (LoRA)
- Finetuning LLMs with LoRA and QLoRA: Insights from Hundreds of Experiments
Applying RL techniques to improve reasoning and decision-making capabilities in language models.
- The State of Reinforcement Learning for LLM Reasoning
- Understanding Reasoning LLMs
- Demystifying Reasoning Models ** also related with rl
- verl: Volcano Engine Reinforcement Learning for LLMs
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
Integration of semantic search and retrieval capabilities into the LLM generation process.
- langchain-ai/rag-from-scratch
- Tutorial: Building your own retrieval-augmented generation system - llms deep dive
- Hands-On-Large-Language-Models - Chapter 8 - Semantic Search and Retrieval-Augmented Generation
- Building an LLM open source search engine in 100 lines using LangChain and Ray
Understanding and mitigating false or misleading outputs from language models.
- 2311 - A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions - v2
- 2409 - LLMs Will Always Hallucinate, and We Need to Live With This - article
- Low-Rank Adaptation Blog Code
- Blog: Finetuning LLaMA Adapters Code
- LLMs from Scratch Appendix E Notebook
- Advanced_RAG : Advanced Retrieval-Augmented Generation (RAG) through practical notebooks, using the power of the Langchain, OpenAI GPTs ,META LLAMA3 ,Agents
- RagBook Notebooks
- New to LLMs? → Start with Learning Resources
- Want to fine-tune efficiently? → Check out PEFT
- Building RAG systems? → Go to RAG section
- Working on agents? → Visit AI Agents
- Production deployment? → See LLMOps
- Need code examples? → Browse Implementation Resources