transformers
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.
- Version
- 1.5
- License
- Apache-2.0 license
- Compatibility
- Requires Python 3.10+, PyTorch 2.5+, and transformers 5.18.0; optional librosa 1.0 requires Python 3.12+. Network access for Hub downloads. Gated or private Hub models need an HF token (`hf auth login` or `HF_TOKEN`).
Pinned to revision 68105dd992f1, so it is the text this page describes rather than whatever the author pushed since.
Pre-approved tools experimental
Experimental field. Support varies between clients, so this list is what the author declared, not what your client will enforce.
- Read
- Write
- Edit
- Bash
Files
- skills/transformers/SKILL.md
- skills/transformers/SKILL_CN.md
- skills/transformers/references/generation.md
- skills/transformers/references/models.md
- skills/transformers/references/pipelines.md
- skills/transformers/references/review.md
- skills/transformers/references/tokenizers.md
- skills/transformers/references/training.md
Every link opens the file at its source, pinned to the revision this page describes.