Hugging Face

Access and work with machine learning datasets from the Hugging Face Hub.

Train and fine-tune language models using TRL or Unsloth on Hugging Face Jobs infrastructure with SFT, DPO, and GGUF conversion.

Run Hugging Face models locally with llama.cpp support for GGUF quantization across CPU, GPU, and Metal.

Build and deploy applications on Hugging Face Spaces with Gradio, Docker, GPU acceleration, and model hosting.

Run pre-trained machine learning models for NLP, vision, and audio tasks directly in JavaScript and TypeScript.