Update app.py

app.py

@@ -10,8 +10,8 @@ pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 def chat(user_input, history=[]):
     prompt = f"{user_input}"
-    result = pipe(prompt, max_new_tokens=200, do_sample=True, temperature=0.8)
-    response = result[0]["generated_text"].replace(prompt, "").strip()
+    result = pipe(prompt, max_new_tokens=100, do_sample=True, temperature=0.8)
+    response = result[0]["generated_text"]
     history.append((user_input, response))
     return history, history