tokens

app/model_loader.py

@@ -17,7 +17,7 @@ def load_model():
 
     base_model = AutoModelForCausalLM.from_pretrained(
         "meta-llama/Llama-2-7b-chat-hf",
-        use_auth_token=hf_token,
+        token=hf_token,
         cache_dir="/tmp/hf_cache",
         torch_dtype="auto",
         device_map="auto"
@@ -25,12 +25,12 @@ def load_model():
     model = PeftModel.from_pretrained(
         base_model,
         "BrainGPT/BrainGPT-7B-v0.1",
-        use_auth_token=hf_token,
+        token=hf_token,
         cache_dir="/tmp/hf_cache"
     )
     tokenizer = AutoTokenizer.from_pretrained(
         "meta-llama/Llama-2-7b-chat-hf",
-        use_auth_token=hf_token,
+        token=hf_token,
         cache_dir="/tmp/hf_cache"
     )
     return model, tokenizer