Alterlab Transformers

Loads, runs, and fine-tunes pretrained models with Hugging Face Transformers v5 (PyTorch-only) — pipeline() inference for chat-model text generation, text classification, NER, zero-shot, speech recognition, image classification, object detection, and image-text-to-text VLMs; AutoModel/AutoTokenizer loading with dtype, device_map and bitsandbytes quantization; generate() decoding control; and Trainer fine-tuning with optional PEFT/LoRA. Use when running inference with a Hugging Face Hub checkpoint, fine-tuning BERT/ModernBERT/Qwen-style models on a custom labelled dataset, controlling generatio

87 stars 18 forksImages, Video & Audio Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add AlterLab-IEU/AlterLab-Academic-Skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-transformers
Manual install
git clone --depth 1 https://github.com/AlterLab-IEU/AlterLab-Academic-Skills.git /tmp/AlterLab-Academic-Skills
mkdir -p ~/.claude/skills
cp -r /tmp/AlterLab-Academic-Skills/skills/data-science/alterlab-transformers ~/.claude/skills/alterlab-transformers

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Transformers

## Overview

Hugging Face Transformers loads pretrained checkpoints from the Hub for NLP, vision, audio, and multimodal tasks, runs inference through `pipeline()` or the `Auto*` classes, and fine-tunes them with `Trainer`. This skill targets **transformers v5** (≥ 5.0; current 5.17.0 as of 2026-09). v5 is PyTorch-only and changes several v4 idioms, so check "v5 changes that break v4 code" below before reusing older snippets from papers, blogs, or model cards.

## When to Use This Skill

Use this skill when the user wants to:
- Run quick inference with a Hub checkpoint via `pipeline()` — text classification, NER, zero-shot classification, text generation with a chat model, speech recognition, image classification/detection, or image-text-to-text with a VLM.
- Load a model plus tokenizer/processor with explicit `dtype`, `device_map`, attention backend, or 4/8-bit quantization.
- Control decoding in `model.generate()` (greedy, sampling, beam search, streaming, chat templates).
- Fine-tune an encoder or decoder on a custom labelled dataset with `Trainer`, optionally with LoRA via `peft`.
- Port v4-era code (`torch_dtype=`, `load_in_8bit=`, removed pipelines, TF/Flax models) to v5.

### Does NOT Trigger

| Scenario | Use Instead |
|----------|-------------|
| Classical ML on tabular features (random forests, preprocessing pipelines, CV grid search) | `alterlab-scikit-learn` |
Read the full skill on GitHub

Details

Skill name
alterlab-transformers
Path
skills/data-science/alterlab-transformers/SKILL.md
License
MIT
Repo updated
11 November 2026

FAQ

What does the Alterlab Transformers skill do?

Loads, runs, and fine-tunes pretrained models with Hugging Face Transformers v5 (PyTorch-only) — pipeline() inference for chat-model text generation, text classification, NER, zero-shot, speech recognition, image classification, object detection, and image-text-to-text VLMs; AutoModel/AutoTokenizer loading with dtype, device_map and bitsandbytes quantization; generate() decoding control; and Trainer fine-tuning with optional PEFT/LoRA. Use when running inference with a Hugging Face Hub checkpoint, fine-tuning BERT/ModernBERT/Qwen-style models on a custom labelled dataset, controlling generatio

How do I install the Alterlab Transformers skill?

Claude Code plugin: /plugin marketplace add AlterLab-IEU/AlterLab-Academic-Skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Alterlab Transformers popular?

It lives in AlterLab-IEU/AlterLab-Academic-Skills, which has 87 GitHub stars and 18 forks, and is included in 1 curated skill list.

Related skills

Alterlab Abm Mesa

87

AlterLab-IEU/AlterLab-Academic-Skills

Builds agent-based models of social systems with Mesa 3 — the current AgentSet API (model.agents.shuffle_do('step'), auto-assigned unique_id, mandatory super().__init__(rng=...)), cell spaces (mesa.discrete_space OrthogonalMooreGrid / classic mesa.space grids), the DataCollector, batch_run parameter sweeps, and SolaraViz — for emergence, segregation, diffusion, opinion dynamics, and cooperation models. It uses the Mesa 3.x API (the old mesa.time schedulers like RandomActivation are removed) and treats the model as a generative theory to be validated, not just run. Use when the request mentions

Research & ScienceIn 1 list18

Alterlab Academic Career

87

AlterLab-IEU/AlterLab-Academic-Skills

Prepares academic career documents and professional-development materials for faculty and researchers. Use when drafting academic CVs, research statements, teaching philosophies, diversity statements, faculty-position cover letters, tenure dossiers, promotion narratives, academic portfolios, or mentorship statements, and when planning conference-networking strategy, building academic web presence, setting up ORCID profiles, or understanding impact metrics. Part of the AlterLab Academic Skills suite.

Research & ScienceIn 1 list18

Alterlab Accreditation Aol

87

AlterLab-IEU/AlterLab-Academic-Skills

Scaffolds program-level Assurance-of-Learning (AoL) documentation for AACSB (Standard 5 in the 2020 standards and the 2026 Global Standards) and ABET (Criterion 3 Student Outcomes, Criterion 4 Continuous Improvement) accreditation — program learning outcomes / competency goals, curriculum-to-outcome mapping matrices, direct- and indirect-assessment plans, rubric design, and closing-the-loop continuous-improvement narratives — and validates the structure of an outcome-mapping matrix with scripts/aol_matrix.py. Use when the user needs AACSB or ABET assurance-of-learning material, a program-learn

Learning & EducationIn 1 list18

Alterlab Zinc Db

87

AlterLab-IEU/AlterLab-Academic-Skills

Access the ZINC database of 230M+ commercially available (purchasable) compounds, searching by ZINC ID or SMILES, running similarity searches, and downloading 3D-ready structures. Use when assembling a compound library for virtual screening, finding purchasable analogs, or obtaining docking-ready 3D structures for drug discovery. Part of the AlterLab Academic Skills suite.

Images, Video & AudioIn 1 list18

Alterlab Pdb

87

AlterLab-IEU/AlterLab-Academic-Skills

Access the RCSB Protein Data Bank (PDB) for EXPERIMENTALLY determined 3D structures (X-ray, cryo-EM, NMR) of proteins and nucleic acids — searching by text, sequence, or structure similarity and downloading coordinates in PDB/mmCIF format with metadata. Use when retrieving a structure by PDB ID, running sequence or structure similarity searches, or obtaining experimental coordinates for structural biology and drug discovery; for AI-PREDICTED structures of proteins lacking experimental data prefer alterlab-alphafold-db, and for protein sequences, annotations, or accession ID mapping prefer alte

Images, Video & AudioIn 1 list18

Qwen Image

51

agentbay-ai/agentbay-skills

Generate images using Qwen Image API (Alibaba Cloud DashScope). Use when users request image generation with Chinese prompts or need high-quality AI-generated images from text descriptions.

Images, Video & AudioIn 1 list

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.