Update app.py

app.py

@@ -8,13 +8,12 @@ MODEL_NAME = "Qwen/Qwen2.5-7B-Instruct"
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_NAME,
-    torch_dtype=torch.float16,
-    device_map="auto"
+    torch_dtype=torch.float32,  # از float32 استفاده کن تا روی CPU اجرا بشه
 )
 
 # تابع چت‌بات
 def chat_with_qwen(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    inputs = tokenizer(prompt, return_tensors="pt")
     output = model.generate(**inputs, max_new_tokens=200)
     response = tokenizer.decode(output[0], skip_special_tokens=True)
     return response