OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

P Tuning

P Tuning is a Python code and dataset repository for parameter-efficient prompt-tuning experiments on pretrained language models, including LAMA and few-shot SuperGLUE (32-dev).

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

P Tuning — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use P Tuning when you want repository-based code and data for the named LAMA or few-shot SuperGLUE experiments and are prepared to follow the requirements in their respective subdirectories.

Who it is for

  • Developers exploring prompt tuning for pretrained language models.
  • Researchers reproducing or adapting the repository’s LAMA and few-shot SuperGLUE experiments.

Documented uses

  • Prepare LAMA data in the repository’s specified data directory.
  • Set up the documented few-shot SuperGLUE dataset in the project root.
  • Use the project code and datasets as a starting point for language-model prompt-tuning experiments.
Before you choose

Requirements & limits

The public repository is licensed under MIT.

  • Experiment requirements are organized in relevant subdirectories, so consult their README and requirement.txt files rather than assume one shared setup.
  • The README specifies different dataset locations: ./data for LAMA and the project root for SuperGLUE.
  • The repository identifies Python as its primary language; the supplied materials do not establish a public API or supported operating systems.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare the LAMA or SuperGLUE experiment data

Place the named dataset in the repository location specified for its experiment.

Before you start

  • The P Tuning repository
  • The LAMA dataset or FewGLUE_32dev SuperGLUE dataset
  • The relevant subdirectory README and requirement.txt for experiment details

Steps

  1. Choose the LAMA or few-shot SuperGLUE (32-dev) experiment.

  2. For LAMA, place its dataset in the project’s ./data directory.

  3. For SuperGLUE, place the dataset in the project root.

  4. Consult the relevant subdirectory README and requirement.txt for further experiment-specific instructions.

Expected outcome

The selected dataset is located where the repository README specifies, with the relevant documentation identified for the next experiment steps.

Guide limitations

  • These instructions cover dataset placement and where to find experiment requirements; they do not provide a complete run command or guarantee an experiment result.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
THUDM/P-tuning · Official homepage title · retained in its source language
How we review sourcesSuggest a correction