Update app.py

app.py

@@ -5,14 +5,14 @@ import torch
 
 class ModelInput(BaseModel):
     prompt: str
-    max_new_tokens: int = 64000
+    max_new_tokens: int = 128000
 
 app = FastAPI()
 
 # Initialize text generation pipeline
 generator = pipeline(
     "text-generation",
-    model="deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+    model="Qwen/Qwen3-4B-Thinking-2507",
     device="cpu"  # Use CPU (change to device=0 for GPU)
 )