Awesome LLMs

A small and humble repo trying to collect awesome resources about Large Language Models and more!

work in constant progress...

Models

• HuggingFace Models
• xAI
  • open Grok-1
  • Grok-1.5
• Mistral
  • open Mixtral 8x7B
  • open Mistral 7B
• Anthropic
  • docs Welcome to Claude - Anthropic
  • api API reference
• Google
• OpenAI
• Meta
  • Meta Llama on HuggingFace

How GPT works?

• What Is ChatGPT Doing … and Why Does It Work?

Prompt Engineering

• Prompt Engineering Guide by DAIR.AI

OpenAI's resources

• Best practices for prompt engineering with the OpenAI API
• GPT-4 Turbo in the OpenAI API
• Knowledge in GPTs
• Retrieval Augmented Generation (RAG) and Semantic Search for GPTs
• OpenAI's Embeddings
• cookbook OpenAI Cookbook
• Moderation API

Frameworks

• LangChain - LangChain is a framework for developing applications powered by language models.
  • book LangChain AI Handbook By James Briggs & Francisco Ingham - Pinecone
  • tutorials LangChain Tutorial page
  • cookbook LangChain Cookbook
  • LangChain Templates
• docs LlamaIndex - LlamaIndex is a data framework for LLM-based applications which benefit from context augmentation.

Tools

• Unstructured
  • github unstructured - Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Development, testing and deploying AI systems

• docs LangSmith Docs LangSmith is a platform for building production-grade LLM applications.
  • LangSmith Pricing
• Instructor, Generating Structure from LLMs - Instructor makes it easy to reliably get structured data like JSON from Large Language Models

for AI Agents

• Tavily AI - Tavily Search API is a search engine optimized for LLMs and RAG, aimed at efficient, quick and persistent search results
  • docs Tavily API
  • docs GPT Researcher
  • github GPT Researcher GitHub page

Tokenizers and tokenization

• tiktoken - fast BPE tokenizer created by OpenAI.
• Byte pair encoding

Embeddings

• The Ins and Outs of Working with Embeddings and Embedding Models

Text splitting

• tool ChunkViz v0.1

Vector Databases

• article Best 16 Vector Databases for 2024
• Vector databases - OpenAI Cookbook
• The Top 5 Vector Databases - DataCamp Article
• A gentle introduction to Vector Databases - Weaviate Blog
• Weaviate.io
• Milvus
  • Milvus - Quick start
• chroma
  • chroma - Getting started
• qdrant
  • qdrant Quickstart

RAG and giving models a long-term memory

• Stanford CS25: V3 I Retrieval Augmented Language Models - YT
• RAFT: Adapting Language Model to Domain Specific RAG
  • github [RAFT code] (https://github.com/ShishirPatil/gorilla/tree/main/raft)
  • LinkedIn post by Andrew Jardine (Hugging Face)
• Massive Text Embedding Benchmark from Hugging Face

Forecasting and Time Series

• Time-LLM: Reprogram an LLM for Time Series Forecasting

LLM Testing and Evaluation

• Needle In A Haystack - Pressure Testing LLMs
• video Is RAG Really Dead? Testing Multi Fact Retrieval & Reasoning in GPT4-128k
  • github Multi Needle In A Haystack Evaluation + LangSmith - rendered IPyNotebook on Github

LLM Security

• What Anthropic’s Sleeper Agents study means for LLM apps

Libraries

• OpenAI Python API library
• OpenAI Node API Library
• tiktoken - tiktoken is a fast BPE tokeniser for use with OpenAI's models.

(Academic) Papers

• A Survey of Large Language Models
• RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
• RAFT: Adapting Language Model to Domain Specific RAG
• RAGAS: Automated Evaluation of Retrieval Augmented Generation
• Attention Is All You Need
• Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
• Efficient Streaming Language Models with Attention Sinks
• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• A General Theoretical Paradigm to Understand Learning from Human Preferences

Managing costs and resources

• The REAL cost of LLM (And How to reduce 78%+ of Cost)

Articles

• article Preference Tuning LLMs with Direct Preference Optimization Methods

Other

• Named Entity Recognition (NER)
  • @Wikipedia
  • What is Named Entity Recognition (NER)? Methods, Use Cases, and Challenges - DataCamp

Companies and their AI solutions/products

• Prolego is an elite team of AI engineers and creative technologists that has been transforming the world's largest companies since 2017.
  • report LLM Optimization Playbook

Learn - standing on the shoulders of giants

Big text files

• shakespeare.txt - Complete Work of William Shakespeare

RAG

• article RAG makes LLMs better and equal
• Advanced RAG Techniques
• article Command R: Retrieval-Augmented Generation at Production Scale - Cohere
• article Introducing Command R+: A Scalable LLM Built for Business
• docs Command R

Videos

• Building a Research Assistant from Scratch - LangChain YT Channel
• Hugging Face + Langchain in 5 mins | Access 200k+ FREE AI models for your AI apps - Jason AI
• All You Need To Know About Running LLMs Locally

...to be continued.