Stars
Implementation of GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022).
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Reference PyTorch implementation and models for DINOv3
Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2
PyTorch code and models for the DINOv2 self-supervised learning method.
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
No fortress, purely open ground. OpenManus is Coming.
Fully open reproduction of DeepSeek-R1
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
🤗 Evaluate: A library for easily evaluating machine learning models and datasets.
A simple, easy-to-hack GraphRAG implementation
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
TrustRAG：The RAG Framework within Reliable input,Trusted output
Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
Chai-1, SOTA model for biomolecular structure prediction
Secrets of RLHF in Large Language Models Part I: PPO
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
[ICCV 2025] LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning
This project shows how to derive the total number of training tokens from a large text dataset from 🤗 datasets with Apache Beam and Dataflow.