Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Vanna AI Streamlit App

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

Instant answers to any programming question

Ollama Python library

Build resilient language agents as graphs.

Superfast AI decision making and intelligent processing of multi-modal data.

A new maintained "successor" to scikit-multilearn, a scikit-learn based module for multi-label et. al. classification

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

Open source codebase powering the HuggingChat app

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

A Python library to extract tabular data from PDFs

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Fine-tuning LLM on my Telegram chats

Fine-tune a large language model on your own iMessages

A research toolkit for particle swarm optimization in Python

LangChain chat model abstractions for dynamic failover, load balancing, chaos engineering, and more!

Discover, try, install and share Streamlit re-usable bits we call "extras"!

Extra blocks for scikit-learn pipelines.

Build AI-powered applications with React, Svelte, Vue, and Solid

Mamba SSM architecture

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

Go ahead and axolotl questions

Set-of-Mark Prompting for LMMs

Examples in the MLX framework

MLX: An array framework for Apple silicon

3D Visualization of an GPT-style LLM