Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-import json
+\
 from nltk.tokenize import sent_tokenize
 import torch
 import ujson as json
@@ -15,11 +15,7 @@ model_name = "decapoda-research/llama-7b-hf"
 adapters_name = 'timdettmers/guanaco-7b'
 # print(f"Starting to load the model {model_name} into memory")
 m = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    #load_in_4bit=True,
-    torch_dtype=torch.bfloat16,
-    device_map='auto'
-)
+    model_name)
 m = PeftModel.from_pretrained(m, adapters_name)
 m = m.merge_and_unload()
 tok = LlamaTokenizer.from_pretrained(model_name)