metadata
library_name: transformers
tags: []
Model Card for Model ID
A version of GPT-2 trained with a differential linear transformer. See https://prdev.substack.com/p/differential-linear-attention?r=2hyugh for details.
library_name: transformers
tags: []
A version of GPT-2 trained with a differential linear transformer. See https://prdev.substack.com/p/differential-linear-attention?r=2hyugh for details.