Stars
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
An AI agent that writes (actually useful) code for you
Causal Inference for the Brave and True. A light-hearted yet rigorous approach to learning about impact estimation and causality.
☁️ Build multimodal AI applications with cloud-native stack
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
pyinfra turns Python code into shell commands and runs them on your servers. Execute ad-hoc commands and write declarative operations. Target SSH servers, local machine and Docker containers. Fast …
AI driven development in your terminal. Designed for large, real-world tasks.
aider is AI pair programming in your terminal
Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
A guidance language for controlling large language models.
⭐️ A friendly language for building type-safe, scalable systems!
DSPy: The framework for programming—not prompting—foundation models
Master programming by recreating your favorite technologies from scratch.
Machine Learning Engineering Open Book
Enforce the output format (JSON Schema, Regex etc) of a language model
Official Python port of Sqids. Generate short unique IDs from numbers.
Instruct-tune LLaMA on consumer hardware
S-LoRA: Serving Thousands of Concurrent LoRA Adapters
The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Typer, build great CLIs. Easy to code. Based on Python type hints.
Large Language Model Text Generation Inference
Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.