runtime error

Exit code: 1. Reason: r/local/lib/python3.10/site-packages/gradio/helpers.py", line 553, in get_final_item async for x in self.fn(*args): # noqa: B007 # type: ignore File "/usr/local/lib/python3.10/site-packages/gradio/chat_interface.py", line 1114, in _examples_stream_fn async for response in generator: File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 751, in __anext__ return await anyio.to_thread.run_sync( File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2476, in run_sync_in_worker_thread return await future File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 967, in run result = context.run(func, *args) File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 734, in run_sync_iterator_async return next(iterator) File "/usr/local/lib/python3.10/site-packages/gradio/external_utils.py", line 146, in chat_fn handle_hf_error(e) File "/usr/local/lib/python3.10/site-packages/gradio/external_utils.py", line 323, in handle_hf_error raise Error(str(e)) from e gradio.exceptions.Error: '{\'code\': \'bad_request\', \'message\': "Request exceeds model context window for \'HuggingFaceH4/zephyr-7b-beta\'. Your prompt is 16 tokens plus max_tokens=32768 = 32784 total, which exceeds the model\'s context size of 32768 tokens by 16 tokens. Reduce max_tokens to at most 32752 or shorten the prompt. (Platform records context_length as 8192; upstream deployment reports 32768.)"}' Traceback (most recent call last): File "/home/user/app/app.py", line 6, in <module> ).launch() File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2707, in launch raise Exception( Exception: Couldn't start the app because 'http://localhost:7860/gradio_api/startup-events' failed (code 500). Check your network or proxy settings to ensure localhost is accessible.

Container logs: