Update README.md

README.md

@@ -42,7 +42,7 @@ model = AutoModelForCausalLM.from_pretrained(
 ).to("cuda" if torch.cuda.is_available() else "cpu")  # Send model to GPU if available
 
 # 🛠 **Define Inference Function**
-def generate_response(model, tokenizer, prompt, max_new_tokens=3200, temperature=0.7):
+def generate_response(model, tokenizer, prompt, max_new_tokens=4096, temperature=0.7):
     
     # Tokenize input
     inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True).to(model.device)