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

llama : support Jamba

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-05-24 19:27:27 -04:00
parent 7e13f19fb5
commit cbc743e600
5 changed files with 606 additions and 123 deletions
Download patch file Download diff file Expand all files Collapse all files

7
gguf-py/gguf/gguf_writer.py
View file

@ -385,8 +385,11 @@ class GGUFWriter:
def add_head_count(self, count: int) -> None:
self.add_uint32(Keys.Attention.HEAD_COUNT.format(arch=self.arch), count)
def add_head_count_kv(self, count: int) -> None:
self.add_uint32(Keys.Attention.HEAD_COUNT_KV.format(arch=self.arch), count)
def add_head_count_kv(self, count: int | Sequence[int]) -> None:
if isinstance(count, int):
self.add_uint32(Keys.Attention.HEAD_COUNT_KV.format(arch=self.arch), count)
else:
self.add_array(Keys.Attention.HEAD_COUNT_KV.format(arch=self.arch), count)
def add_key_length(self, length: int) -> None:
self.add_uint32(Keys.Attention.KEY_LENGTH.format(arch=self.arch), length)