ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

convert : fix duplicate key DeepSeek-R1 conversion error (#14103)

Browse source
This commit is contained in:
Sigbjørn Skjæret 2025-06-10 23:29:52 +02:00 • committed by GitHub
parent 3678b838bb
commit 55f6b9fa65
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 5 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

7
convert_hf_to_gguf.py
View file

@ -556,8 +556,11 @@ class TextModel(ModelBase):
logger.info(f"gguf: experts used count = {n_experts_used}")
if (head_dim := self.hparams.get("head_dim")) is not None:
self.gguf_writer.add_key_length(head_dim)
self.gguf_writer.add_value_length(head_dim)
# Workaround for incorrect AutoConfig value for DeepSeekV3 (is set correctly in DeepSeekV2Model class)
# https://github.com/huggingface/transformers/blob/19224c3642705c5b6988c9f5f4251f83323d05ae/src/transformers/models/deepseek_v3/configuration_deepseek_v3.py#L210
if self.hparams.get("model_type") != "deepseek_v3":
self.gguf_writer.add_key_length(head_dim)
self.gguf_writer.add_value_length(head_dim)
self.gguf_writer.add_file_type(self.ftype)
logger.info(f"gguf: file type = {self.ftype}")