Update app.py

app.py

@@ -5,7 +5,7 @@ import torch
 
 class ModelInput(BaseModel):
     prompt: str
-    max_new_tokens: int = 2048
+    max_new_tokens: int = 64000
 
 app = FastAPI()
 
@@ -13,13 +13,13 @@ app = FastAPI()
 generator = pipeline(
     "text-generation",
     model="deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
-    device=1  # Use CPU (change to device=0 for GPU)
+    device=0  # Use CPU (change to device=0 for GPU)
 )
 
 # Create text streamer
 streamer = TextStreamer(generator.tokenizer, skip_prompt=True)
 
-def generate_response(prompt: str, max_new_tokens: int = 2048):
+def generate_response(prompt: str, max_new_tokens: int = 64000):
     try:
         messages = [{"role": "user", "content": prompt}]
         output = generator(messages, max_new_tokens=max_new_tokens, do_sample=False, streamer=streamer)