Transformers

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.

skills.sh installs: 2.1K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill transformers --agent claude-code

Installs into .claude/skills of the current project.

Files

Transformers

Overview

The Hugging Face Transformers library provides access to thousands of pre-trained models for tasks across NLP, computer vision, audio, and multimodal domains. Use this skill to load models, perform inference, and fine-tune on custom data.

Installation

Targets Transformers 5.18.0, verified against its released source on 2026-10-01. Native CPU checks use Python 3.11, Torch 2.14.1, Datasets 5.0.1, Accelerate 1.15.0, PEFT 0.21.2, and Hub 1.33.0. The Torch extra requires Torch >=2.5. Install in a dedicated environment:

uv venv --python 3.11 .venv-transformers
uv pip install --python .venv-transformers/bin/python "transformers[torch]==5.18.0" "torch==2.14.1" "huggingface-hub==1.33.0" "datasets==5.0.1" "accelerate==1.15.0" "peft==0.21.2"

Use .venv-transformers/Scripts/python.exe on Windows. Select an appropriate Torch build for the target hardware before installation. Hub 2.1.1 is newer, but Datasets 5.0.1 requires Hub <2; upgrading every package independently makes this training stack unsatisfiable. The separate esm SDK currently requires Transformers <5 and belongs in another environment.

SKILL.md on GitHub