google-research/prompt-tuning
Research implementation of Prompt Tuning, a parameter-efficient technique for adapting large pre-trained language models by training soft prompt embeddings.
Not currently ranked — collecting fresh signals.
star history
This repository contains the original Google Research implementation of Prompt Tuning from the EMNLP 2021 paper. The technique enables efficient adaptation of large pre-trained language models (T5) by training soft prompt embeddings rather than modifying all model parameters. The implementation builds on T5X for model and training logic, Flaxformer for model computation, Flax for low-level layers, and JAX for execution. It provides code for training prompts, performing inference with trained prompts, and includes released model checkpoints and prompts.
Frequently asked
- What is google-research/prompt-tuning?
- Research implementation of Prompt Tuning, a parameter-efficient technique for adapting large pre-trained language models by training soft prompt embeddings.
- Is prompt-tuning open source?
- Yes — google-research/prompt-tuning is open source, released under the Apache-2.0 license.
- What language is prompt-tuning written in?
- google-research/prompt-tuning is primarily written in Python.
- How popular is prompt-tuning?
- google-research/prompt-tuning has 701 stars on GitHub.
- Where can I find prompt-tuning?
- google-research/prompt-tuning is on GitHub at https://github.com/google-research/prompt-tuning.