Update app.py

app.py

@@ -49,7 +49,7 @@ class GradioInference:
  self.tokenizer = AutoTokenizer.from_pretrained("csebuetnlp/mT5_multilingual_XLSum", truncation=True)
  self.model = AutoModelForSeq2SeqLM.from_pretrained("csebuetnlp/mT5_multilingual_XLSum")
 
- self.config = {'max_new_tokens': 128, 'repetition_penalty': 1.1, 'temperature':0}
+ self.config = {'repetition_penalty': 1.1, 'temperature':0}
  self.llm = CTransformers(model="TheBloke/Llama-2-7B-Chat-GGML", model_file = 'llama-2-7b-chat.ggmlv3.q2_K.bin', config=self.config,callbacks=[StreamingStdOutCallbackHandler()])