replica
/
llama.cpp
mirror of https://github.com/ggml-org/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

convert : correct gemma 3n conversion (#14450) 

* convert : correct gemma 3n conversion

* rm redundant code
This commit is contained in:
Xuan-Son Nguyen 2025-07-03 10:03:06 +02:00 committed by GitHub
parent a70c8a0c4b
commit 0c2ee38ab7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
gguf-py/gguf/gguf_writer.py
View File

@ -714,8 +714,8 @@ class GGUFWriter:
def add_clamp_kqv(self, value: float) -> None:
self.add_float32(Keys.Attention.CLAMP_KQV.format(arch=self.arch), value)
def add_shared_kv_layers(self, value: float) -> None:
self.add_float32(Keys.Attention.SHARED_KV_LAYERS.format(arch=self.arch), value)
def add_shared_kv_layers(self, value: int) -> None:
self.add_uint32(Keys.Attention.SHARED_KV_LAYERS.format(arch=self.arch), value)
def add_sliding_window_pattern(self, value: Sequence[bool]) -> None:
self.add_array(Keys.Attention.SLIDING_WINDOW_PATTERN.format(arch=self.arch), value)