#
Starred repositories
An interface library for RL post training with environments.
A lightweight express.js server implementing OpenAI’s Responses API, built on top of Chat Completions, powered by Hugging Face Inference Providers.
A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗
Making a mini version of the BDX droid. https://discord.gg/UtJZsgfQGe
A library for working with prompt templates locally or on the Hugging Face Hub.
A Lightweight Library for AI Observability
Easy, fast and very cheap training and inference on AWS Trainium and Inferentia chips.
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
Speech To Speech: an effort for an open-sourced and modular GPT4-o
A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation
A library for easily merging multiple LLM experts, and efficiently train the merged LLM.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Minimalistic large language model 3D-parallelism training
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
A high-throughput and memory-efficient inference and serving engine for LLMs
Simple, safe way to store and distribute tensors
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Use Hugging Face with JavaScript
Large Language Model Text Generation Inference
Used for adaptive human in the loop evaluation of language and embedding models.
Stable Diffusion web UI
python library for invisible image watermark (blind image watermark)
Efficient few-shot learning with Sentence Transformers
skops is a Python library helping you share your scikit-learn based models and put them in production