Update app.py

app.py

@@ -17,24 +17,19 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto",
 )
 
-cache = {}
 
 @app.post("/generate")
 async def generate(request: Request):
     data = await request.json()
     prompt = data.get("prompt", "").strip()
 
-    if prompt in cache:
-        return {"output": cache[prompt], "cached": True}
-
+  
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
     outputs = model.generate(
         inputs.input_ids,
         max_new_tokens=100,
         use_cache=True,
-        do_sample=True,
-        top_p=0.95,
-        top_k=50,
+    
         temperature=0.7,
     )