Downloads · 30 days
76
1% of all-time downloads
Mixtral-8x22B-Instruct-v0.1-GPTQ-4bit
jarrelscy/Mixtral-8x22B-Instruct-v0.1-GPTQ-4bit
Mixtral-8x22B-Instruct-v0.1-GPTQ-4bit is a text generation model from jarrelscy. Use it when you need the model to write or continue text. It is set up for transformers.
Optimum GPTQ quantized 8-bit version of Mixtral-8x22B-Instruct-v0.1 \ See original model card for more information.
All-time downloads
5.2K
Public
Parameters
141B
148 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors73.8 GB · 100%
Parameter types
How the weights are stored.
I32140B · 100%
Try a prompt
Model card
From the Hugging Face model README
Model Card for Model ID
Optimum GPTQ quantized 8-bit version of Mixtral-8x22B-Instruct-v0.1
See original model card for more information.
How to load
- Task
- Text Generation
- Library
- transformers
- Type
- mixtral
- Created
- Apr 20, 2024
- Updated
- May 5, 2024