How to enable the sending of 100K tokens for codellama
harlequen opened this issue · comments
Hi, I'm testing codellama, and I would like a guide on how to enable it to accept the sending of 100K input tokens. From what I understand, this is done by adjusting the max_seq_len
and max_batch_size
parameters, but I couldn't find more information on this. Please, if someone could guide me.
As an extra question, do you know what the default size it would accept is?
Thank you, and I will appreciate any help.