Skip to content
Skills Library
AI & agents · Building & coding

transformers

/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.

Repository
openscience ↗
Licence
Apache-2.0
Last repository change
25.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
6
Scripts
0
HTML comments
0
URLs in SKILL.md
1
Deprecation

No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

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.

Original author description

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.

How it works

  1. Overview
  2. Installation
  3. Credential Setup
  4. Quick Start
  5. Core Capabilities
  6. Common Patterns
  7. Reference Documentation
Original SKILL.md headings · 149 lines, 538 words
SKILL.md preview
---
name: transformers
description: 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.
category: llm-tools
license: Apache-2.0 license
compatibility: Some features require an Huggingface token
metadata:
    upstream: K-Dense-AI/scientific-agent-skills
    upstream-url: https://github.com/K-Dense-AI/scientific-agent-skills
    upstream-path: skills/transformers
    upstream-license: MIT
    upstream-relationship: derived
    adapted-by: Synthetic Sciences
    skill-author: K-Dense Inc.
version: 1.0.0
author: K-Dense Inc.
tags: [NLP, Deep Learning, Hugging Face, LLM, Fine-Tuning]
dependencies: ["transformers>=4.45.0", "torch>=2.0.0", "tokenizers>=0.19.0"]
---

# 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

Install transformers and core dependencies:

```bash
uv pip install torch transformers datasets evaluate accelerate
```

For vision tasks, add:
```bash
uv pip install timm pillow
```

For audio tasks, add:
```bash
uv pip install librosa soundfile
```

## Credential Setup

HuggingFace token is auto-injected by openscience when connected via the dashboard.

```bash
# Verify credentials
[ -n "$HF_TOKEN" ] && echo "HF_TOKEN set" || echo "NOT SET"
```

If not set: add your Hugging Face token in Customize → Tools or export `HF_TOKEN` locally.

## Quick Start

Use the Pipeline API for fast inference without manual configuration:

```python
from transformers import pipeline

# Text generation
generator = pipeline("text-generation", model="gpt2")
result = generator("The future of AI is", max_length=50)

# Text classification
classifier = pipeline("text-classification")
result = classifier("This movie was excellent!")

# Question answering
qa = pipeline("question-answering")
result = qa(question="What is AI?", context="AI is artificial intelligence...")
```

## Core Capabilities

### 1. Pipelines for Quick Inference

Use for simple, optimized inference across many tasks. Supports text generation, classification, NER, question answering, summarization, translation, image classification, object detection, audio classification, and more.

**When to use**: Quick prototyping, simple inference tasks, no custom preprocessing needed.

See `references/pipelines.md` for comprehensive task coverage and optimization.

### 2. Model Loading and Management

Load pre-trained models with fine-grained control over configuration, device placement, and precision.

**When to use**: Custom model initialization, advanced device management, model inspection.

See `references/models.md` for loading patterns and best practices.

### 3. Text Generation

Generate text with LLMs using various decoding strategies (greedy, beam search, sampling) and control parameters (temperature, top-k, top-p).

**When to use**: Creative text generation, code generation, conversational AI, text completion.

See `references/generation.md` for generation strategies and parameters.

### 4. Training and Fine-Tuning

Fine-tune pre-trained models on custom datasets using the Trainer API with automatic mixed precision, distributed training, and logging.

**When to use**: Task-specific model adaptation, domain adaptation, improving model performance.

See `references/training.md` for training workflows and best practices.

### 5. Tokenization

Convert text to tokens and token IDs for model input, with padding, truncation, and special token handling.

**When to use**: Custom preprocessing pipelines, understanding model inputs, batch processing.

See `references/tokenizers.md` for tokenization details.

## Common Patterns

### Pattern 1: Simple Inference
For straightforward tasks, use pipelines:
```python
pipe = pipeline("task-name", model="model-id")
output = pipe(input_data)
```

### Pattern 2: Custom Model Usage
For advanced control, load model and tokenizer separately:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("model-id")
model = AutoModelForCausalLM.from_pretrained("model-id", device_map="auto")

inputs = tokenizer("text", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
result = tokenizer.decode(outputs[0])
```

### Pattern 3: Fine-Tuning
For task adaptation, use Trainer:
```python
from transformers import Trainer, TrainingArguments

training_args = TrainingArguments(
    output_dir="./results",
    num_train_epochs=3,
    per_device_train_batch_size=8,
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset,
)

trainer.train()
```

## Reference Documentation

For detailed information on specific components:
- **Pipelines**: `references/pipelines.md` - All supported tasks and optimization
- **Models**: `references/models.md` - Loading, saving, and configuration
- **Generation**: `references/generation.md` - Text generation strategies and parameters
- **Training**: `references/training.md` - Fine-tuning with Trainer API
- **Tokenizers**: `references/tokenizers.md` - Tokenization and preprocessing
Files in this package (6)
  • SKILL.md 5 KB
  • references/generation.md 9 KB
  • references/models.md 8 KB
  • references/pipelines.md 9 KB
  • references/tokenizers.md 10 KB
  • references/training.md 10 KB

Versions

RepositoryScoreLicence
This page · synthetic-sciences/openscience100Apache-2.0
lamm-mit/scienceclaw100Apache-2.0
bestagentkits/agency-skills100MIT
davila7/claude-code-templates95MIT

Database snapshot: 13.11.2026 · package version 9acc48cfe71b (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 95transformers-js
    Runs Hugging Face models in JavaScript or TypeScript with Transformers.js, in the browser or Node, Bun and Deno via WebGPU or WASM: text classification, translation, summarisation, image classification, object detection, speech recognition and multimodal tasks. Use when the user…
  • 95huggingface-transformers
    Hugging Face Transformers best practices including model loading, tokenization, fine-tuning workflows, and inference optimization. Use when working with transformer models, fine-tuning LLMs, implementing NLP tasks, or optimizing transformer inference.
  • 100alterlab-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;…
  • 100transformers-inference
    HuggingFace Transformers for model inference. Use when: text classification, NER, question answering, summarization, embeddings, zero-shot classification. NOT for: training large models (use cloud), simple regex/rule-based tasks, production serving at scale (use vLLM).
  • 100processing-computer-vision-tasks
    Process images using object detection, classification, and segmentation. Use when requesting "analyze image", "object detection", "image classification", or "computer vision". Trigger with relevant phrases based on skill purpose.
  • 100processing-computer-vision-tasks
    Process images using object detection, classification, and segmentation. Use when requesting "analyze image", "object detection", "image classification", or "computer vision". Trigger with relevant phrases based on skill purpose.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.