tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-13 06:23:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

gguf-py : add support for chat template jinja files (#14508)

Browse Source 
* add support for chat template jinja files

* remove gemma3n hack
This commit is contained in:
Sigbjørn Skjæret
2025-07-02 21:02:35 +02:00
committed by GitHub
parent 5d46babdc2
commit e75ba4c043
2 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
convert_hf_to_gguf.py
View File

@ -4408,9 +4408,6 @@ class Gemma3NModel(Gemma3Model):
]
def set_vocab(self):
with open(self.dir_model / "chat_template.jinja") as f:
# quick hack to make sure chat template is added
self.gguf_writer.add_chat_template(f.read())
super().set_vocab()
def set_gguf_parameters(self):