P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks
Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training. However, in the context of NLU, prior work reveals that prompt tuning does not perform well for normal-sized pretrained models. We also find that existing methods of prompt tuning cannot handle hard sequence labeling tasks, indicating a lack of universality. We present a novel empirical finding that properly optimized prompt tuning can be universally effective across a wide range of model scales and NLU tasks. It matches the performance of finetuning while having only 0.1%-3% tuned parameters. Our method P-Tuning v2 is an implementation of Deep Prompt Tuning \cite{li2021prefix,qin2021learning} optimized and adapted for NLU. Given the universality and simplicity of P-Tuning v2, we believe it can serve as an alternative to finetuning and a strong baseline for future research.Our code and data are released at https://github.com/THUDM/P-tuning-v2.
Code (5)
Tasks
Language ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks
Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training. However, in the context of NLU, prior work reveals that prompt tuning …
Language ModelingLanguage ModellingInput-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models
Recently the prompt-tuning paradigm has attracted significant attention. By only tuning continuous prompts with a frozen pre-trained language model (PLM), prompt-tuning takes a step towards deploying a shared frozen PLM …
Language ModelingLanguage ModellingNatural Language UnderstandingText GenerationPrompt Tuning for Generative Multimodal Pretrained Models
Prompt tuning has become a new paradigm for model tuning and it has demonstrated success in natural language pretraining and even vision pretraining. In this work, we explore the transfer of prompt tuning to multimodal p…
Image CaptioningVisual EntailmentVisual Question Answering (VQA)Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models
Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. In this work, we show that finetuning LMs in the few-shot setting can consi…
Few-Shot LearningPrompt EngineeringSkeleton: A New Framework for Accelerating Language Models via Task Neuron Localized Prompt Tuning
Prompt tuning methods have shown comparable performance to general training methods as parameter-efficient fine-tuning (PEFT) methods in various natural language understanding tasks. However, existing prompt tuning metho…
Language ModelingLanguage ModellingNatural Language Understandingparameter-efficient fine-tuning