nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 18 Packages Projects Releases Wiki Activity

convert : support Gemma4ForCausalLM architecture (#23682)

Browse Source 
* convert : support Gemma4ForCausalLM architecture (#23674)

* fix indent

---------

Co-authored-by: Oleg Afonin <your.email@example.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
ghleg
2026-05-26 08:00:31 +03:00
committed by GitHub
co-authored by Oleg Afonin Sigbjørn Skjæret
parent 6fe90deffa
commit dbe9c0c8ce
2 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
conversion/gemma.py
+1 -1
View File
@@ -614,7 +614,7 @@ class Gemma3NModel(Gemma3Model):
yield from super().modify_tensors(data_torch, name, bid)
@ModelBase.register("Gemma4ForConditionalGeneration")
@ModelBase.register("Gemma4ForConditionalGeneration", "Gemma4ForCausalLM")
class Gemma4Model(Gemma3Model):
model_arch = gguf.MODEL_ARCH.GEMMA4