Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-\
+
 from nltk.tokenize import sent_tokenize
 import torch
 import ujson as json
@@ -18,7 +18,7 @@ m = AutoModelForCausalLM.from_pretrained(
     model_name,
     load_in_4bit=True)
 m = PeftModel.from_pretrained(m, adapters_name)
-m = m.merge_and_unload()
+#m = m.merge_and_unload()
 tok = LlamaTokenizer.from_pretrained(model_name)
 tok.bos_token_id = 1
 stop_token_ids = [0]