PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917622175498240 |
|---|---|
| author | Li, Jinyi Lan, Yihuai Wang, Lei Wang, Hao |
| author_facet | Li, Jinyi Lan, Yihuai Wang, Lei Wang, Hao |
| contents | Prompt compression is an innovative method for efficiently condensing input prompts while preserving essential information. To facilitate quick-start services, user-friendly interfaces, and compatibility with common datasets and metrics, we present the Prompt Compression Toolkit (PCToolkit). This toolkit is a unified plug-and-play solution for compressing prompts in Large Language Models (LLMs), featuring cutting-edge prompt compressors, diverse datasets, and metrics for comprehensive performance evaluation. PCToolkit boasts a modular design, allowing for easy integration of new datasets and metrics through portable and user-friendly interfaces. In this paper, we outline the key components and functionalities of PCToolkit. We conducted evaluations of the compressors within PCToolkit across various natural language tasks, including reconstruction, summarization, mathematical problem-solving, question answering, few-shot learning, synthetic tasks, code completion, boolean expressions, multiple choice questions, and lies recognition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17411 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models Li, Jinyi Lan, Yihuai Wang, Lei Wang, Hao Computation and Language Prompt compression is an innovative method for efficiently condensing input prompts while preserving essential information. To facilitate quick-start services, user-friendly interfaces, and compatibility with common datasets and metrics, we present the Prompt Compression Toolkit (PCToolkit). This toolkit is a unified plug-and-play solution for compressing prompts in Large Language Models (LLMs), featuring cutting-edge prompt compressors, diverse datasets, and metrics for comprehensive performance evaluation. PCToolkit boasts a modular design, allowing for easy integration of new datasets and metrics through portable and user-friendly interfaces. In this paper, we outline the key components and functionalities of PCToolkit. We conducted evaluations of the compressors within PCToolkit across various natural language tasks, including reconstruction, summarization, mathematical problem-solving, question answering, few-shot learning, synthetic tasks, code completion, boolean expressions, multiple choice questions, and lies recognition. |
| title | PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.17411 |