CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases 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
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
convert_hf_to_gguf.py
View File

@@ -556,6 +556,9 @@ class TextModel(ModelBase):
logger.info(f"gguf: experts used count = {n_experts_used}")
if (head_dim := self.hparams.get("head_dim")) is not None:
# 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)