switch to Qwen2.5-7B-Instruct

server.py

@@ -20,7 +20,7 @@ def _pick_free_gpu():
 if __name__ == "__main__":
     _pick_free_gpu()
 
-    model = str(Path(__file__).resolve().parent / "models/GLM-4.6V-Flash")
+    model = str(Path(__file__).resolve().parent / "models/Qwen2.5-7B-Instruct")
 
     os.environ["FLASHINFER_DISABLE_VERSION_CHECK"] = "1"
 
@@ -29,14 +29,14 @@ if __name__ == "__main__":
         model,
         "--host", "0.0.0.0",
         "--port", "8000",
-        "--served-model-name", "GLM-4.6V-Flash",
+        "--served-model-name", "Qwen2.5-7B-Instruct",
         "--trust-remote-code",
-        "--enable-auto-tool-choice",
-        "--tool-call-parser", "glm47",
         "--max-model-len", "32768",
         "--dtype", "bfloat16",
         "--gpu-memory-utilization", "0.85",
         "--enforce-eager",
+        "--enable-auto-tool-choice",
+        "--tool-call-parser", "openai",
         "--generation-config", "vllm",
         "--override-generation-config", '{"temperature": 0.8, "top_k": 50, "top_p": 0.9}',
     ])