https://github.com/kipgparker/soft-prompt-tuning

https://github.com/kipgparker/soft-prompt-tuning

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/kipgparker/soft-prompt-tuning
• Owner: kipgparker
• License: mit
• Created: 2021-04-22T20:24:33.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2021-08-08T21:01:57.000Z (over 3 years ago)
• Last Synced: 2024-06-24T05:49:49.631Z (5 months ago)
• Language: Jupyter Notebook
• Size: 43 KB
• Stars: 326
• Watchers: 5
• Forks: 44
• Open Issues: 9
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• StarryDivineSky - soft-prompt-tuning - Efficient Prompt Tuning 用于参数高效的即时调整的规模的力量 (其他_NLP自然语言处理 / 其他_文本生成、文本对话)

README

        
# The Power of Scale for Parameter-Efficient Prompt Tuning



Implementation of soft embeddings from https://arxiv.org/abs/2104.08691v1 using Pytorch and Huggingface transformers

# Citation

```bibtex

@misc{lester2021power,

      title={The Power of Scale for Parameter-Efficient Prompt Tuning}, 

      author={Brian Lester and Rami Al-Rfou and Noah Constant},

      year={2021},

      eprint={2104.08691},

      archivePrefix={arXiv},

      primaryClass={cs.CL}

}

```