Manoranjan Rajguru
Manoranjan Rajguru
I am also looking at the same . I want to predict various page segments like Tables , Header , Paragraph , Charts etc . Can you please share some...
Now if i decrease the max-batch-prefill-tokens it says MAX_INPUT_LENGTH cant be more than max-batch-prefill-tokens
Hi @Narsil , Wanted to understand more about the concept here. Its a 13b model which takes around 25GB of memory. I have g5.48xlarge with 192 GB of memory. How...
what is your TGI version , i am using 0.9.3
I am facing the same issue. When are we planning to merge this to master ?
@csellis could you please share the working notebook if possible or the line I need to change .
anyplan on supporting mosaicml/mpt-30b-instruct ?
any plan on supporting mosaicml/mpt-30b-instruct support
Let me get the info :)