🤗 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.

A high-throughput and memory-efficient inference and serving engine for LLMs

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

⚡ A Fast, Extensible Progress Bar for Python and CLI

A generative world for general-purpose robotics & embodied AI learning.

Fully open reproduction of DeepSeek-R1

SGLang is a fast serving framework for large language models and vision language models.

State-of-the-Art Text Embeddings

Train transformer language models with reinforcement learning.

verl: Volcano Engine Reinforcement Learning for LLMs

Minimal reproduction of DeepSeek R1-Zero

Open source annotation tool for machine learning practitioners.

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

A Collection of Variational Autoencoders (VAE) in PyTorch.

An open source library for deep learning end-to-end dialog systems and chatbots.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Open-source implementation of AlphaEvolve

An open-source framework for training large multimodal models.

Environments for LLM Reinforcement Learning

【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Python library for loading and using triangular meshes.

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions