Update app.py

app.py

@@ -7,5 +7,15 @@ import bitsandbytes as bnb
 from transformers import GenerationConfig
 from transformers import AutoTokenizer, AutoConfig, LlamaForCausalLM, LlamaTokenizer
 
+tokenizer = LlamaTokenizer.from_pretrained("wxjiao/alpaca-7b")
+
+model2 = LlamaForCausalLM.from_pretrained(
+    "wxjiao/alpaca-7b",
+    load_in_8bit=True,
+    device_map="auto",
+)
+
+
+