From: Sigbjørn Skjæret <redacted>
Date: Tue, 10 Jun 2025 21:29:52 +0000 (+0200)
Subject: convert : fix duplicate key DeepSeek-R1 conversion error (#14103)
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=55f6b9fa6563f6ae49113f9abdc980c12348cc1c;p=pkg%2Fggml%2Fsources%2Fllama.cpp

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

diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index a208c42b..173a103b 100755
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -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}")