root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-30 13:24:35 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

convert-hf : make actual types match annotations

Browse Source
This commit is contained in:
Jared Van Bortel 2024-03-01 15:19:59 -05:00
parent c29af7e225
commit 95845d17ec
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
convert-hf-to-gguf.py
View File

@ -1679,7 +1679,7 @@ class BertModel(Model):
else: else:
raise NotImplementedError("Only MEAN and CLS pooling types supported") raise NotImplementedError("Only MEAN and CLS pooling types supported")
self.gguf_writer.add_pooling_type(pooling_type.value) self.gguf_writer.add_pooling_type(pooling_type)
def set_vocab(self): def set_vocab(self):
path = self.dir_model path = self.dir_model

2
gguf-py/gguf/gguf_writer.py
View File

@ -362,7 +362,7 @@ class GGUFWriter:
self.add_bool(Keys.Attention.CAUSAL.format(arch=self.arch), value) self.add_bool(Keys.Attention.CAUSAL.format(arch=self.arch), value)
def add_pooling_type(self, value: PoolingType) -> None: def add_pooling_type(self, value: PoolingType) -> None:
self.add_uint32(Keys.LLM.POOLING_TYPE.format(arch=self.arch), value) self.add_uint32(Keys.LLM.POOLING_TYPE.format(arch=self.arch), value.value)
def add_rope_dimension_count(self, count: int) -> None: def add_rope_dimension_count(self, count: int) -> None:
self.add_uint32(Keys.Rope.DIMENSION_COUNT.format(arch=self.arch), count) self.add_uint32(Keys.Rope.DIMENSION_COUNT.format(arch=self.arch), count)