mpt-30b-chat

#1
by rabidaught - opened

Can you do the same for mpt-30b-chat?

It actually scores much higher than the instruct version .

Might take a bit, having a slow internet connection (20Mbit Upload)

Thank you.
Does GeneratorCT2 support loading the model into multiple GPUs?
Right now at 30Gb this model is too large for a single consumer grade GPU.

This is not possible yet - see issue: https://github.com/OpenNMT/CTranslate2/issues/1052

michaelfeil changed discussion status to closed

Sign up or log in to comment