vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

convert : support models with multiple chat templates (#6588)

Browse source 
* Support converting models with multiple chat templates

Adds the following metadata:
* tokenizer.chat_templates
* tokenizer.chat_template.<name1>
* tokenizer.chat_template.<name2>
* tokenizer.chat_template.<...>

Where `tokenizer.chat_templates` is an array of the template names (except `default`), `default` is added to the regular `tokenizer.chat_template`.

* replace filtered characters with underscore

* New script to add/modify/remove metadata

This scripts creates a copy of a GGUF file and allows you to add/modify/remove metadata in the process.

Most importantly this allows you to update chat templates, either as a string or directly from an updated tokenizer_config.json file.

* Add files via upload

add new script to project/readme

* flake--
This commit is contained in:
Sigbjørn Skjæret 2024-04-18 13:49:01 +02:00 • committed by GitHub
parent e11b2e6e1e
commit 03c0946d73
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 226 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

1
gguf-py/pyproject.toml
View file

@ -33,3 +33,4 @@ build-backend = "poetry.core.masonry.api"
gguf-convert-endian = "scripts:gguf_convert_endian_entrypoint"
gguf-dump = "scripts:gguf_dump_entrypoint"
gguf-set-metadata = "scripts:gguf_set_metadata_entrypoint"
gguf-new-metadata = "scripts:gguf_new_metadata_entrypoint"