Update app.py

app.py

@@ -114,7 +114,7 @@ def qa(question):
     outputs =  model.generate(prompt=prompt, temp=0.5, top_k = 40, top_p = 1, max_tokens = max_new_tokens)"""
 
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-    tokens = model.generate(**inputs, max_length=100, do_sample=True, top_p=0.95, top_k=60, temperature=0.3)
+    tokens = model.generate(**inputs, max_length=1000, do_sample=True, top_p=0.95, top_k=60, temperature=0.3)
     
 
     return tokenizer.decode(tokens[0])