Manoranjan Rajguru

Results 19 comments of 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

anyplan on supporting mosaicml/mpt-30b-instruct ?

any plan on supporting mosaicml/mpt-30b-instruct support