ge3

main.py

@@ -46,7 +46,7 @@ async def generate_text(request: RequestData):
     try:
         output = generator(
             request.prompt,
-            max_new_tokens=min(request.max_tokens, 100),
+            max_new_tokens=min(request.max_tokens, 10000),
             do_sample=False,
             num_beams=1,
             temperature=0.7,