fix: Correct the mtmd vision check condition bug

Author: JamePeng

llama_cpp/llama_chat_format.py

@@ -2892,8 +2892,9 @@ def _init_mtmd_context(self, llama_model: llama.Llama):
                 raise ValueError(f"{self.log_prefix}(_init_mtmd_context): Failed to load mtmd context from: {self.clip_model_path}")
 
             # Check if vision is supported
-            if self._mtmd_cpp.mtmd_support_vision(self.mtmd_ctx) and self.verbose:
-                print(f"{self.log_prefix}(_init_mtmd_context): Vision support detected.", file=sys.stderr)
+            if self._mtmd_cpp.mtmd_support_vision(self.mtmd_ctx):
+                if self.verbose:
+                    print(f"{self.log_prefix}(_init_mtmd_context): Vision support detected.", file=sys.stderr)
             else:
                 raise ValueError("Vision is not supported by this model")
             # Check if audio is supported