Downloads · 30 days
10
19% of all-time downloads
CognitiveFusion_4x7b_MoE_Exl2_8.0BPW
SytanSD/CognitiveFusion_4x7b_MoE_Exl2_8.0BPW
CognitiveFusion_4x7b_MoE_Exl2_8.0BPW is a text generation model from SytanSD. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
I found CognitiveFusion when searching for new models to use for instruct and roleplay based ineractions. This model blew me way instantly, and I knew I had to make some exl2 quants for it. I have held onto these for…
All-time downloads
53
Public
Repo size
24.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors24.3 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mixtral
- Access
- Public
- Created
- Mar 18, 2024
- Updated
- Mar 18, 2024
- SHA
- 004fd98e
Try a prompt
Model card
From the Hugging Face model README
I found CognitiveFusion when searching for new models to use for instruct and roleplay based ineractions. This model blew me way instantly, and I knew I had to make some exl2 quants for it. I have held onto these for a while, as I have been out of my element uploading model cards to HF, but I finally decided to jump in. As of now I have only created 8.0BPW and 3.5BPW quants, but I do have plans to create 3.0, 4.0, 4.5, and 6.0 BPW quants when I am able to.
- Task
- Text Generation
- Library
- transformers
- Type
- mixtral
- License
- apache-2.0
- Languages
- en
- Created
- Mar 18, 2024
- Updated
- Mar 18, 2024