runtime error

turn await get_async_backend().run_sync_in_worker_thread( File "/home/user/.local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2134, in run_sync_in_worker_thread return await future File "/home/user/.local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 851, in run result = context.run(func, *args) File "/home/user/.local/lib/python3.10/site-packages/gradio/utils.py", line 689, in wrapper response = f(*args, **kwargs) File "/home/user/.local/lib/python3.10/site-packages/gradio/external.py", line 352, in query_huggingface_inference_endpoints data = fn(*data) # type: ignore File "/home/user/.local/lib/python3.10/site-packages/gradio/external_utils.py", line 115, in text_generation_inner return input + client.text_generation(input) File "/home/user/.local/lib/python3.10/site-packages/huggingface_hub/inference/_client.py", line 1535, in text_generation raise_text_generation_error(e) File "/home/user/.local/lib/python3.10/site-packages/huggingface_hub/inference/_text_generation.py", line 534, in raise_text_generation_error raise http_error File "/home/user/.local/lib/python3.10/site-packages/huggingface_hub/inference/_client.py", line 1511, in text_generation bytes_output = self.post(json=payload, model=model, task="text-generation", stream=stream) # type: ignore File "/home/user/.local/lib/python3.10/site-packages/huggingface_hub/inference/_client.py", line 240, in post hf_raise_for_status(response) File "/home/user/.local/lib/python3.10/site-packages/huggingface_hub/utils/_errors.py", line 333, in hf_raise_for_status raise HfHubHTTPError(str(e), response=response) from e huggingface_hub.utils._errors.HfHubHTTPError: 500 Server Error: Internal Server Error for url: https://api-inference.huggingface.co/models/vishnukv/llama2-3b-4k (Request ID: S-ZV6NDC-duU7xAi70EYP) `rope_scaling` must be a dictionary with with two fields, `type` and `factor`, got {'factor': 16.0, 'original_max_position_embeddings': 4096, 'type': 'yarn'}

Container logs: