llama.cpp
4cd621c2 - convert : add BPE pre-tokenization for DBRX (#7132)

Comment changes are shownComment changes are hidden
Commit
1 year ago
convert : add BPE pre-tokenization for DBRX (#7132) * Add BPE pre-tokenization for DBRX. * Add vocab GGUFs. * Remove test. * Remove GGUFs.
Author
Parents
  • File
    convert-hf-to-gguf-update.py
  • File
    convert-hf-to-gguf.py
  • File
    llama.cpp
  • File
    llama.h