ucinlp/autoprompt

AutoPrompt: Automatic Prompt Construction for Masked Language Models.

46
/ 100
Emerging

This project helps NLP practitioners automatically craft the best prompts for large language models to perform specific tasks. It takes raw text data (like customer reviews or factual statements) and outputs highly effective prompt templates. This is useful for data scientists and NLP researchers who want to quickly evaluate a model's inherent ability to handle tasks like sentiment analysis, natural language inference, or fact extraction without extensive fine-tuning.

641 stars. No commits in the last 6 months.

Use this if you need to rapidly discover how well a masked language model can perform various NLP tasks by generating optimal prompts for zero-shot or few-shot learning.

Not ideal if you are looking for a tool to fine-tune language models with labeled data or build custom models from scratch.

Natural Language Processing Sentiment Analysis Fact Extraction Prompt Engineering Text Classification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

641

Forks

86

Language

Python

License

Apache-2.0

Last pushed

Aug 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/ucinlp/autoprompt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.