Downloads · 30 days
11
19% of all-time downloads
Mistral-22B-v0.1-bnb-4bit
Ba2han/Mistral-22B-v0.1-bnb-4bit
Mistral-22B-v0.1-bnb-4bit is a text generation model from Ba2han. Use it when you need the model to write or continue text. It is set up for transformers.
This is a 4 bit quantized version of Vezora/Mistral-22B-v0.1.
All-time downloads
59
Public
Parameters
22.9B
12.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors12.1 GB · 100%
Parameter types
How the weights are stored.
U822.5B · 98%
Try a prompt
Model card
From the Hugging Face model README
This is a 4 bit quantized version of Vezora/Mistral-22B-v0.1.
I don't know if it works properly for training. I could not get it to work using Unsloth - it gives OOM error even with very low settings.
According to Vezora there will be a better version coming up soon anyways. Uploading this for fun.
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- Created
- Apr 12, 2024
- Updated
- Apr 12, 2024