promptsource and OpenPrompt

These are complements: OpenPrompt provides a framework for implementing prompt-learning methods across different model architectures, while PromptSource supplies curated, reusable prompt templates and datasets that can be integrated into OpenPrompt pipelines for evaluation and experimentation.

promptsource
57
Established
OpenPrompt
56
Established
Maintenance 0/25
Adoption 11/25
Maturity 25/25
Community 21/25
Maintenance 0/25
Adoption 11/25
Maturity 25/25
Community 20/25
Stars: 3,007
Forks: 380
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 4,837
Forks: 486
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
Stale 6m
Stale 6m

About promptsource

bigscience-workshop/promptsource

Toolkit for creating, sharing and using natural language prompts.

This toolkit helps natural language processing practitioners create, share, and use specialized text prompts for large language models. You input raw text data and a prompt, and it outputs the data formatted as a question or instruction ready for a language model to process. This is ideal for researchers, data scientists, or AI engineers working on fine-tuning or evaluating large language models.

natural-language-processing prompt-engineering language-model-evaluation text-data-preparation AI-experimentation

About OpenPrompt

thunlp/OpenPrompt

An Open-Source Framework for Prompt-Learning.

This framework helps developers quickly build and experiment with 'prompt-learning' for various natural language processing tasks. It takes raw text inputs and a pre-trained language model, then processes them through customizable templates and verbalizers to produce task-specific outputs like sentiment labels or generated text. The end users are machine learning engineers and researchers who are working on fine-tuning large language models for specific applications.

natural-language-processing machine-learning-engineering language-model-fine-tuning AI-model-development

Scores updated daily from GitHub, PyPI, and npm data. How scores work