Update app.py

app.py

@@ -35,7 +35,7 @@ def load_llm():
 
     model_name = 'mistralai/Mistral-7B-Instruct-v0.2'
 
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    tokenizer = AutoTokenizer.from_pretrained(model_name, token=HF_TOKEN)
     model = AutoModelForCausalLM.from_pretrained(
         model_name,
         #load_in_4bit=True,
@@ -43,6 +43,7 @@ def load_llm():
         torch_dtype=torch.bfloat16,
         device_map="auto",
         trust_remote_code=True,
+        token=HF_TOKEN,
     )
 
     pipe = pipeline(