runtime error

get_async_backend().run_sync_in_worker_thread( File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2144, in run_sync_in_worker_thread return await future File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 851, in run result = context.run(func, *args) File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 751, in wrapper response = f(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/gradio/external.py", line 357, in query_huggingface_inference_endpoints data = fn(*data) # type: ignore File "/usr/local/lib/python3.10/site-packages/gradio/external_utils.py", line 115, in text_generation_inner return input + client.text_generation(input) File "/usr/local/lib/python3.10/site-packages/huggingface_hub/inference/_client.py", line 1841, in text_generation raise_text_generation_error(e) File "/usr/local/lib/python3.10/site-packages/huggingface_hub/inference/_common.py", line 470, in raise_text_generation_error raise http_error File "/usr/local/lib/python3.10/site-packages/huggingface_hub/inference/_client.py", line 1817, in text_generation bytes_output = self.post(json=payload, model=model, task="text-generation", stream=stream) # type: ignore File "/usr/local/lib/python3.10/site-packages/huggingface_hub/inference/_client.py", line 267, in post hf_raise_for_status(response) File "/usr/local/lib/python3.10/site-packages/huggingface_hub/utils/_errors.py", line 371, 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/Qwen/Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4 (Request ID: XoOTXpZ8oqXTLStKp8NGu) The checkpoint you are trying to load has model type `qwen2_moe` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

Container logs: