diff --git a/convert-hf-to-gguf.py b/convert-hf-to-gguf.py
index 852ba5e86..6fbe8067b 100755
--- a/convert-hf-to-gguf.py
+++ b/convert-hf-to-gguf.py
@@ -1314,6 +1314,8 @@ class PersimmonModel(Model):
             self.gguf_writer.add_tensor(new_name, data)
 @Model.register("LlamaForCausalLM")
 class DeepseekCoderModel(Model):
+    model_arch = gguf.MODEL_ARCH.LLAMA
+    
     def set_gguf_parameters(self):
         super().set_gguf_parameters()
         head_count = self.hparams["num_attention_heads"]
diff --git a/models/ggml-vocab-deepseek-coder.gguf b/models/ggml-vocab-deepseek-coder.gguf
index 2531e1e19..640ee63d8 100644
Binary files a/models/ggml-vocab-deepseek-coder.gguf and b/models/ggml-vocab-deepseek-coder.gguf differ