#33 · Primary category： NLP Tools & Text Processing
OpenPrompt
An Open-Source Framework for Prompt-Learning.
Project last updated：07/16/24
GitHub Stars
4.9K
Forks
476
Contributors
24
License
Apache-2.0
Why we included this project
OpenPrompt is a prompt-learning framework built on PyTorch and Hugging Face transformers. It keeps templates, the text you wrap around an input, separate from verbalizers, the mapping from label words to the model's vocabulary, so you can test a prompting idea without rewriting your experiment code. Swapping BERT for RoBERTa or T5 means changing the model argument, not the pipeline. The library comes with processors and a trainer for common NLP tasks, which is a real time-saver when you want to reproduce results from prompt-learning papers instead of building the scaffolding yourself. It also pairs with UltraChat for supervised instruction tuning, and it won the ACL 2022 Best Demo Paper Award. For teams comparing prompting strategies across several models, this is a practical foundation.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
compromise
modest natural-language processing
tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
CoreNLP
CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.
Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量