diff options
| author | Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> | 2024-04-18 13:49:01 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-18 14:49:01 +0300 |
| commit | 03c0946d73c63ea73e1d85015b7088298443d438 (patch) | |
| tree | 3add06ebc5f14022771887ca0bce636b39ff8633 /gguf-py/scripts/__init__.py | |
| parent | e11b2e6e1e18522ca7cf129600875a0f6fb9307d (diff) | |
convert : support models with multiple chat templates (#6588)
* 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--
Diffstat (limited to 'gguf-py/scripts/__init__.py')
| -rw-r--r-- | gguf-py/scripts/__init__.py | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/gguf-py/scripts/__init__.py b/gguf-py/scripts/__init__.py index 77132db7..1ad45639 100644 --- a/gguf-py/scripts/__init__.py +++ b/gguf-py/scripts/__init__.py @@ -8,5 +8,6 @@ os.environ["NO_LOCAL_GGUF"] = "TRUE" gguf_convert_endian_entrypoint = import_module("scripts.gguf-convert-endian").main gguf_dump_entrypoint = import_module("scripts.gguf-dump").main gguf_set_metadata_entrypoint = import_module("scripts.gguf-set-metadata").main +gguf_new_metadata_entrypoint = import_module("scripts.gguf-new-metadata").main del import_module, os |