What problem does it solve? Working with pre-trained machine learning models across NLP, vision, audio, and multimodal tasks requires navigating complex model loading, tokenization, and training APIs. This Skill provides structured guidance for using the Hugging Face Transformers library to perform inference and fine-tuning without deep framework expertise. ## Core Features & Use Cases - Pipeline-Based Inference: Run text generation, classification, question answering, translation, summarization, image classification, object detection, and speech recognition with minimal code. - Custom Model Loading: Load models and tokenizers with fine-grained control over device placement, precision, and configuration using AutoModel classes. - Fine-Tuning with Trainer API: Adapt pre-trained models to custom datasets with automatic mixed precision, distributed training, and logging. - Use Case: A developer needs to classify customer support tickets by intent. They load a pre-trained text-classification pipeline, test it on sample tickets, then fine-tune the model on their labeled dataset using the Trainer API. ## Quick Start Use the transformers skill to load a pre-trained text classification model and classify the sentiment of a given sentence.
