Update app.py

app.py

@@ -15,7 +15,7 @@ def getLLamaresponse(input_text):
     #prompt = "I want to drink water"
 
     # Run text generation pipeline with the model
-    pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=50, do_sample=True)
+    pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=50, do_sample=True, repetition_penalty=1.9)
     result = pipe(f"<s>[INST] {input_text} [/INST]")
     # print(result[0]['generated_text'])
     return result[0]['generated_text']