wow
#1
by
Danioken
- opened
Your model is doing great for only 12B, would you consider doing something similar with the mistral small 3.1 24B? Nemo lacks a bit of intelligence to pin some details, the Mistral small would be better at that... Plus I'd really like to see what you could do with this model.
Don't have the funds nor the Compute for the model as of now.
https://ko-fi.com/deltavector
If you want, you can donate to my ko-fi and i'll be able to do one in the future. I need something that i can stick into 1 16gb gpu anyway
Danioken
changed discussion status to
closed