patch output (again) and fix token limit

app.py

@@ -34,13 +34,13 @@ def llm(msgs):
     ]
     outputs = llama(
         prompt,
-        max_new_tokens=10,
+        max_new_tokens=100,
         eos_token_id=terminators,
         do_sample=True,
         temperature=0.6,
         top_p=0.9,
     )
-    return outputs[0]["generated_text"]#[len(prompt):]
+    return outputs[0]["generated_text"][len(prompt):]#for the 801100128909120989534879th  time remember to transfer changes between test and app.py -_-
 
 def randomize():
     global randtxt