File size: 301 Bytes
3c14e44 |
1 2 3 4 5 |
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. |