Home/Model Training/P-tuning-v2

P-tuning-v2

THUDM/P-tuning-v2

Optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

GitHub

GraphCanon updated Sep 26, 2026 · GitHub synced Sep 26, 2026

41views this month

2.1k stars212 forksLast push Nov 16, 2023 Python Apache-2.0

Decision brief

P-tuning-v2 is an optimized deep prompt tuning strategy that can be used for tasks like natural language processing and parameter-efficient learning where few parameters need to be adjusted compared to full fine-tuning.

Good fit when

For scenarios requiring efficient use of resources, as P-tuning v2 requires fewer parameters than traditional fine-tuning methods.
When working with small to medium-sized models or tasks that are challenging for sequence tagging where deep prompt tuning can bridge the performance gap without full model fine-tuning.

Avoid when

Avoid using P-tuning v2 when you have large-scale datasets and model architectures, as it might not be as effective compared to full fine-tuning methods.
If your project requires a high level of customization beyond prompt tuning or continuous prompts do not align with the problem complexity.

Requirements:: Min 8 GB RAM; Experiments were conducted on NVIDIA DGX-A100; however, RTX 3090 or RTX 2080 Ti GPUs can suffice given certain conditions.; CUDA version should be at least 11.1 and specific versions of pytorch (1.7.1), torchvision (0.8.2) and torchaudio (0.7.2).; A conda environment setup with Python 3.8.5 is recommended for optimal performance.

Observed Jul 17, 2026 · Source: enrich:decision_facts

P-tuning-v2 alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Dormant (1045d since push); As of Sep 26, 2026
Provenance: Not a fork · Organization account; As of Sep 26, 2026
Security (OSV): 50 low (50 low); As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install P-tuning-v2

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

peft

State-of-the-art Parameter-Efficient Fine-Tuning

22k★

trl

Train transformer language models with reinforcement learning

19k★

oumi

Easily fine-tune, evaluate and deploy open source LLMs/VLMs

9.4k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Repository for P-tuning v2, an optimized prompt tuning approach that provides performance similar to traditional fine-tuning but with fewer parameters.

Capability facts

Languages: python
Source: github.language · Sep 26, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Sep 26, 2026)

conda create -n pt2 python=3.8.5

Source link

README

P tuning v2 Source codes and data for [ACL 2022] P Tuning v2: Prompt Tuning Can Be Comparable to Finetuning Universally Across Scales and Tasks [Findings of EMNLP 2023] Parameter Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers [[Code]](https://gith...

For agents

This page has a .md twin and JSON over the API.

/tools/thudm-p-tuning-v2.md GET /api/graphcanon/tools/thudm-p-tuning-v2 GET /api/graphcanon/graph?tool=thudm-p-tuning-v2