PyTorch implementation of a generative model for high-fidelity audio generation from text prompts.
Zero-shot voice conversion and singing voice conversion with real-time support and fine-tuning capabilities.
Open-source platform for visualizing and analyzing reasoning processes of Large Language Models (LLMs).
Simple, unified interface to multiple Generative AI providers.
Pioneering Multimodal Reasoning with CoT, an open-source model for advanced visual and text reasoning.
A Datacenter Scale Distributed Inference Serving Framework for generative AI and reasoning models.
A curated list of awesome AI assistants with a Telegram bot for testing.
Run your own AI cluster at home with everyday devices.
Hybrid thinking tool for efficient AI model integration in open-webui.
A unified evaluation framework for large language models.
