debug

data/models/llama3-1-8b.py

@@ -18,7 +18,7 @@ pipeline = transformers.pipeline(
     model=model_id,
     model_kwargs={"torch_dtype": torch.bfloat16},
     device=0,
-    hf_token = api_key
+    token = api_key
 )
 
 @app.route('/chat', methods=['POST'])