Multi-modal large language model designed for audio understanding
Implementation of RLHF (Reinforcement Learning with Human Feedback)
Doom-based AI research platform for reinforcement learning
Recognition and resolution of numbers, units, date/time, etc.
Run a full local LLM stack with one command using Docker
Convert codebases into structured prompts optimized for LLM analysis
Volcano Engine Reinforcement Learning for LLMs
AI tool for detecting complex vulnerabilities in Python codebases
Generate typed SDKs from OpenAPI, AsyncAPI, GraphQL, gRPC
Library for efficient similarity search and clustering dense vectors
The open source post-building layer for agents
A Model Context Protocol server for searching and analyzing arXiv
A suite of plugins for legal workflows
Claude + Obsidian knowledge companion
An open-source, GPU-accelerated physics simulation engine
Your Fully-Automated Personal AI Assistant
Communicate with an LLM provider using a single interface
Self-evolving AI agent framework for automated workflows
A general fine-tuning kit geared toward image/video/audio diffusion
Repo of Qwen2-Audio chat & pretrained large audio language model
Tensor search for humans
NeuTTS model built from small LLM backbones
On-device TTS model by Neuphonic
From Addition, Subtraction, Multiplication, and Division to ML