tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-26 03:03:25 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/mamba2

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-10-01 13:09:40 -04:00
parent 273e7a495a f1b8c42711
commit 7d6cb36895
105 changed files with 8055 additions and 5231 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
gguf-py/gguf/gguf_writer.py
View File

@ -670,6 +670,9 @@ class GGUFWriter:
def add_expert_weights_scale(self, value: float) -> None:
self.add_float32(Keys.LLM.EXPERT_WEIGHTS_SCALE.format(arch=self.arch), value)
def add_swin_norm(self, value: bool) -> None:
self.add_bool(Keys.LLM.SWIN_NORM.format(arch=self.arch), value)
def add_rescale_every_n_layers(self, count: int) -> None:
self.add_uint32(Keys.LLM.RESCALE_EVERY_N_LAYERS.format(arch=self.arch), count)