Stars
Official implementation of "PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors"
Our library for RL environments + evals
SGLang is a high-performance serving framework for large language models and multimodal models.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
slime is an LLM post-training framework for RL Scaling.
Textbook on reinforcement learning from human feedback
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase
Scalable toolkit for efficient model reinforcement
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
Fully open reproduction of DeepSeek-R1
ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)
The fastest way to create an HTML app
aider is AI pair programming in your terminal
Sweep: AI coding assistant for JetBrains
Instant voice cloning by MIT and MyShell. Audio foundation model.
Fast and memory-efficient exact attention
FlashInfer: Kernel Library for LLM Serving
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
Prompt, run, edit, and deploy full-stack web applications. -- bolt.new -- Help Center: https://support.bolt.new/ -- Community Support: https://discord.com/invite/stackblitz
A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL
open-source agentic AI data assistant for the next generation of AI + Data products.
Train transformer language models with reinforcement learning.