llama.cpp
Improve handling of special tokens in GGML to GGUF converter
#2725

Merged

Commits

Improve UNK, BOS, EOS token handling when converting without metadata.

KerfuffleV2 committed 2 years ago
Set default UNK token mapping from -1 to 0 in llama.cpp

KerfuffleV2 committed 2 years ago
Try to handle overflow due to buggy Windows Python with a better error message

KerfuffleV2 committed 2 years ago