Load Hugging Face models, run inference pipelines, and fine-tune on custom data across NLP, vision, audio, and multimodal tasks. The skill covers the v5 library (PyTorch-only now, TensorFlow support dropped), so you'll use AutoModel classes, the Pipeline API for quick inference, and Trainer for fine-tuning workflows. Gated models need HF authentication, and some custom architectures require trust_remote_code. Good reference docs break down pipelines, generation strategies, and tokenization patterns. If you're prototyping with pretrained models or adapting them to your domain, this gives you the standard toolchain. Just know transformers v5 changed the backend story, so older TF code won't port directly.
npx skills add https://github.com/k-dense-ai/scientific-agent-skills --skill transformers