We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 926b566 commit d6bd4e0Copy full SHA for d6bd4e0
convert_hf_to_gguf.py
@@ -558,7 +558,7 @@ def set_gguf_parameters(self):
558
if (head_dim := self.hparams.get("head_dim")) is not None:
559
# Workaround for incorrect AutoConfig value for DeepSeekV3 (is set correctly in DeepSeekV2Model class)
560
# https://github.com/huggingface/transformers/blob/19224c3642705c5b6988c9f5f4251f83323d05ae/src/transformers/models/deepseek_v3/configuration_deepseek_v3.py#L210
561
- if self.hparams.get("qk_rope_head_dim") != head_dim:
+ if self.hparams.get("model_type") != "deepseek_v3":
562
self.gguf_writer.add_key_length(head_dim)
563
self.gguf_writer.add_value_length(head_dim)
564
0 commit comments