CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/refactor-kv-cache

Browse Source
This commit is contained in:
Francis Couture-Harpin
2025-07-03 16:03:56 -04:00
parent 908e6559d6 bee28421be
commit 4682e21c46
89 changed files with 895 additions and 4844 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):