Update app.py

app.py

@@ -38,11 +38,11 @@ async def generate_text(request: GenerateRequest):
         with torch.no_grad():
             outputs = model.generate(
                 **inputs,
-                # max_new_tokens=request.max_new_tokens,
-                # temperature=request.temperature,
-                do_sample=True,
+                max_new_tokens=request.max_new_tokens,
+                temperature=request.temperature,
+                # do_sample=True,
                 repetition_penalty=1.1,
-                pad_token_id=tokenizer.eos_token_id
+                # pad_token_id=tokenizer.eos_token_id
             )
         
         full_text = tokenizer.decode(outputs[0], skip_special_tokens=True)