Shypd.aiThe largest open index of AI toolsP-tuning is an open-source method for tuning language models, offering a novel approach to optimize their performance. It includes codes and datasets for the paper "GPT understands, too", supporting models like GLM-130B.
Trending
About
P-tuning is an open-source method designed to tune large language models, providing a novel and efficient approach to enhance their capabilities. It includes the necessary codes and datasets for the research paper "GPT understands, too", demonstrating its practical application. The method supports advanced models such as GLM-130B, which has been shown to outperform GPT-3 175B on various benchmarks. This makes P-tuning a valuable resource for researchers and developers looking to optimize language models with readily available hardware, including configurations like 4 * RTX 3090 or 8 * RTX 2080 Ti. The project also highlights P-tuning v2 and parameter-efficient prompt tuning for neural text retrievers.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
