Closed ehartford closed 1 year ago
I know that you are trying to reproduce llama architecture - but, is there a way to do that but with a change to allow for longer context? we really need 8k context, if not 32k. 2k is too limiting.
duplicate of https://github.com/openlm-research/open_llama/issues/3
I know that you are trying to reproduce llama architecture - but, is there a way to do that but with a change to allow for longer context? we really need 8k context, if not 32k. 2k is too limiting.