veRL: Volcano Engine Reinforcement Learning for LLM

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

Disaggregated serving system for Large Language Models (LLMs).

The largest KG for material science

Lightning-fast serving engine for any AI model of any size. Flexible. Easy. Enterprise-scale.

KaibanJS is a JavaScript-native framework for building and managing multi-agent systems with a Kanban-inspired approach.

从零实现一个小参数量中文大语言模型。

A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.

Multiple Positives and Negatives Ranking Loss

A middleware to provide an openAI compatible endpoint that can call MCP tools

Google AI Studio Starter Apps

This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use".

Building a comprehensive and handy list of papers for GUI agents

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

Smithery connects language models to Model Context Protocols, allowing you to build agents that use resources and tools without being overwhelmed by JSON schemas.

LOTUS: A semantic query engine for fast and easy LLM-powered data processing

implement interactive image predictor using plotly dash

Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

A collection of MCP servers.

Python tool for converting files and office documents to Markdown.

Code for BLT research paper

NVIDIA Ingest is an early access set of microservices for parsing hundreds of thousands of complex, messy unstructured PDFs and other enterprise documents into metadata and text to embed into retri…

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

A very quick project that transforms research papers into engaging three-person discussions, offering an intuitive and thought-provoking listening experience. Perfect for podcast enthusiasts seekin…

An open-source implementation of Anthropic's Computer Use to perform basic tasks using AI Agents.

Model Context Protocol Servers

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)