ggml-org/llama.cpp

feature request - disabling tokenizer in conversion / inference

Chiusa

#1765 aperta il 8 giu 2023

 (7 commenti) (1 reazione) (0 assegnatari)C++ (21.737 fork)batch import
enhancementgood first issuehelp wanted

Metriche repository

Star
 (124.043 stelle)
Metriche merge PR
 (Merge medio 6g 8h) (389 PR mergiate in 30 g)

Descrizione

in #1764 i asked if it'd be possible to add a Huggingface tokenizer. but - HF tokenizers are quite flexible and officially supporting them in llama.cpp (or ggml?) might be a lot of hassle.

a much easier workaround would be allowing to disable tokenizers in both model conversion and inference. this means the users are supposed to encode(text)/decode(ids) in their implementation for using llama.cpp. in my case, for example, i'll use a python GUI and a wrapper anyway.

i'd like to work on it, but honestly i don't think i understand enough to be able to do this. i'd appreciate very much if anyone's interested in it.

Guida contributor