domains / families / science / transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets. Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Applies when working with AutoModel, pipelines, tokenizers, generation configs, or TrainingArguments within Transformers.
The K-Dense-AI copy is a much more specific, version-pinned, and security-aware procedure (Transformers 5.18.0, PyTorch-only, Hub version constraints, hf auth login, HF_TOKEN, trust_remote_code/revision, cache env vars, and a note that v5 removed several pipelines). The other two copies are near-identical generic guides that use older patterns (max_length, question-answering pipeline, HUGGINGFACE_TOKEN) and omit the v5 constraints. Because the K-Dense copy would hide the older but still common v4-style workflow, and the other two would hide the v5 constraints, crowning one would lose a real alternative.