ggml-org/llama.cpp

feature request - disabling tokenizer in conversion / inference

Fechada

#1.765 aberto em 8 de jun. de 2023

 (7 comentários) (1 reação) (0 responsável)C++ (21.874 forks)batch import
enhancementgood first issuehelp wanted

Métricas do repositório

Stars
 (124.541 estrelas)
Métricas de merge de PR
 (Mesclagem média 6d 8h) (389 fundiu PRs em 30d)

Description

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.

Guia do colaborador