license: mit | |
pipeline_tag: feature-extraction | |
This repository contains the GPT-300m described in [Cottention: Linear Transformers With Cosine Attention](https://huggingface.co/papers/2409.18747). | |
license: mit | |
pipeline_tag: feature-extraction | |
This repository contains the GPT-300m described in [Cottention: Linear Transformers With Cosine Attention](https://huggingface.co/papers/2409.18747). | |