Closed kustaaya closed 3 months ago
The changes look correct me, but there are conflicts that need to be resolved before this can be merged. I think it is just because llama.h
and llama.cpp
were moved to a different directory.
The changes look correct me, but there are conflicts that need to be resolved before this can be merged. I think it is just because
llama.h
andllama.cpp
were moved to a different directory.
Thanks! I updated the pull request to fix the conflicts.
Implemented suggested changes from discussion in pull request #7328 by @akx . Added pre-tokenizer support for Viking-models.
Tokenizer is the same for Viking-7B and its 13B and 33B siblings. Fixes issue #7309