Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

model: Add support for Nanbeige4.2 (#25994)

Browse Source 
* support nanbeige4.2 model

* fix

* fix flake8 Lint check

* fix loop bound check and drop redundant head_dim

---------

Co-authored-by: root <lizongqiang@kanzhun.com>
This commit is contained in:
zql
2026-07-27 17:04:18 +02:00
committed by GitHub
co-authored by root
parent 0324696b8e
commit b77d646751
10 changed files with 265 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/gguf_writer.py
+6
View File
@@ -908,6 +908,12 @@ class GGUFWriter:
def add_token_shift_count(self, count: int) -> None:
self.add_uint32(Keys.LLM.TOKEN_SHIFT_COUNT.format(arch=self.arch), count)
def add_num_loops(self, count: int) -> None:
self.add_uint32(Keys.LLM.NUM_LOOPS.format(arch=self.arch), count)
def add_skip_loop_final_norm(self, value: bool) -> None:
self.add_bool(Keys.LLM.SKIP_LOOP_FINAL_NORM.format(arch=self.arch), value)
def add_interleave_moe_layer_step(self, value: int) -> None:
self.add_uint32(Keys.LLM.INTERLEAVE_MOE_LAYER_STEP.format(arch=self.arch), value)