Hugging Face's production-ready toolkit for deploying LLMs. Optimized for high throughput with tensor parallelism, quantization, and Flash Attention.
Hugging Face's state-of-the-art ML library. Access thousands of pretrained models for NLP, computer vision, audio, and multimodal tasks.
Open source AI chat interface by Hugging Face. Chat with the latest open models including LLaMA, Mistral, and Falcon for free.
