transformers

SKILL.md

Transformers is the model-definition framework for state-of-the-art machine learning across text, vision, audio, and multimodal domains. It provides unified APIs for loading pretrained models, running inference, and fine-tuning.

All loading uses frompretrained() which handles downloading, caching, and device placement:

The pipeline() function provides high-level inference with minimal code:

Loading and using pretrained models with Hugging Face Transformers. Use when working with pretrained models from the Hub, running inference with Pipeline API, fine-tuning models with Trainer, or handling text, vision, audio, and multimodal tasks. Source: itsmostafa/llm-engineering-skills.

View raw