Upload app.py

app.py

@@ -12,7 +12,7 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 ACCESS_TOKEN = os.getenv("HF_TOKEN", "")
 
-model_id = "Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8"
+model_id = "Qwen/Qwen2.5-Coder-3B-Instruct"
 
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
@@ -104,7 +104,7 @@ chat_interface = gr.Interface(
             value=1.0,
         ),          
     ],
-    title="Model testing - Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8",
+    title="Model testing - Qwen/Qwen2.5-Coder-3B-Instruct",
     description="Provide system settings and a prompt to interact with the model.",
 )