EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

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
7 changed files with 226 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gguf-py/README.md
View File

@@ -21,6 +21,8 @@ pip install gguf
[scripts/gguf-convert-endian.py](https://github.com/ggerganov/llama.cpp/blob/master/gguf-py/scripts/gguf-convert-endian.py) — Allows converting the endianness of GGUF files.
[scripts/gguf-new-metadata.py](https://github.com/ggerganov/llama.cpp/blob/master/gguf-py/scripts/gguf-new-metadata.py) — Copies a GGUF file with added/modified/removed metadata values.
## Development
Maintainers who participate in development of this package are advised to install it in editable mode: