Stars
🤗 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.
Train transformer language models with reinforcement learning.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
A library for mechanistic interpretability of GPT-style language models
RDFLib is a Python library for working with RDF, a simple yet powerful language for representing information.
Making large AI models cheaper, faster and more accessible
The nnsight package enables interpreting and manipulating the internals of deep learned models.
A library for efficient similarity search and clustering of dense vectors.
An incremental parsing system for programming tools
This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking".
A very simple framework for state-of-the-art Natural Language Processing (NLP)
State-of-the-Art Text Embeddings
mR3: Multilingual Rubric-Agnostic Reward Reasoning Models
Open Source Neural Machine Translation and (Large) Language Models in PyTorch
Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"
An open source library for deep learning end-to-end dialog systems and chatbots.
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
RewardBench: the first evaluation tool for reward models.
A library for advanced large language model reasoning
PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"
⚡ A Fast, Extensible Progress Bar for Python and CLI
Dialog Skill Analysis framework for Watson Assistant