Downloads · 30 days
11
7% of all-time downloads
Cosine_Attention_GPT_300M
gmongaras/Cosine_Attention_GPT_300M
Cosine_Attention_GPT_300M is a feature extraction model from gmongaras. Use it when you need embeddings to search or compare text. The card lists the license as mit.
This repository contains the GPT-Cos-300m model described in Cottention: Linear Transformers With Cosine Attention.
All-time downloads
165
Public
Repo size
2.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Feature Extraction
- License
- mit
- Model type
- gptj
- Access
- Public
- Created
- Oct 7, 2024
- Updated
- Oct 7, 2024
- SHA
- c63c9e27
Model card
From the Hugging Face model README
This repository contains the GPT-Cos-300m model described in Cottention: Linear Transformers With Cosine Attention.
- Task
- Feature Extraction
- Type
- gptj
- License
- mit
- Created
- Oct 7, 2024
- Updated
- Oct 7, 2024