google-research/prompt-tuning
Original Implementation of Prompt Tuning from Lester, et al, 2021
This project helps machine learning engineers and researchers to efficiently customize large language models for specific natural language tasks. Instead of fine-tuning the entire model, you provide input data and a configuration, and it generates small, task-specific "prompts" that guide a pre-trained language model's behavior. This allows for adapting powerful models to new applications without the high computational cost of full model retraining.
697 stars. No commits in the last 6 months.
Use this if you need to adapt very large language models like T5 to new text classification, summarization, or generation tasks with minimal computational overhead and parameter changes.
Not ideal if you need to train a language model from scratch or if you are working with small models where full fine-tuning is already computationally feasible.
Stars
697
Forks
63
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/google-research/prompt-tuning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
thunlp/PromptPapers
Must-read papers on prompt-based tuning for pre-trained language models.
ZhangYuanhan-AI/NOAH
[TPAMI] Searching prompt modules for parameter-efficient transfer learning.
gmkim-ai/PromptKD
An official implementation of "PromptKD: Distilling Student-Friendly Knowledge for Generative...
zhengzangw/DoPrompt
Official implementation of PCS in essay "Prompt Vision Transformer for Domain Generalization"
Hzfinfdu/MPMP
ACL'2023: Multi-Task Pre-Training of Modular Prompt for Few-Shot Learning