You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I also would like somene to try this:
first quantize Mistral-7B-Instruct-v0.3 to q4_k or to q5_1. then train/finetune it on that dataset.
Unfortunately I have no resources to do so.. and not enough know how to do it properly online.
P.S.
I chose mistral because in my opinion it has the best "chat" attitude... although it's lacking in solving logical problems, but it has a great creativity.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
@TheBloke I would love if you or anyone else could train mistralai/Mistral-7B-Instruct-v0.3
on this great dataset: https://huggingface.co/datasets/ZeroWw/MEISD
I also would like somene to try this:
first quantize Mistral-7B-Instruct-v0.3 to q4_k or to q5_1. then train/finetune it on that dataset.
Unfortunately I have no resources to do so.. and not enough know how to do it properly online.
P.S.
I chose mistral because in my opinion it has the best "chat" attitude... although it's lacking in solving logical problems, but it has a great creativity.
Beta Was this translation helpful? Give feedback.
All reactions