vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : initial Mamba-2 support

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-08-01 10:43:42 -04:00
parent a1631e53f6
commit 1f0fea70fb
7 changed files with 490 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -730,6 +730,9 @@ class GGUFWriter:
def add_ssm_time_step_rank(self, value: int) -> None:
self.add_uint32(Keys.SSM.TIME_STEP_RANK.format(arch=self.arch), value)
def add_ssm_group_count(self, value: int) -> None:
self.add_uint32(Keys.SSM.GROUP_COUNT.format(arch=self.arch), value)
def add_ssm_dt_b_c_rms(self, value: bool) -> None:
self.add_bool(Keys.SSM.DT_B_C_RMS.format(arch=self.arch), value)