runtime error

Exit code: 1. Reason: huggingface.co/api/inference-proxy/toge… │ │ │ │ MAX_NUM_ROWS = 50000 │ │ │ │ MAX_NUM_TOKENS = 2048 │ │ │ │ MODEL = 'deepseek-ai/DeepSeek-R1' │ │ │ │ OLLAMA_BASE_URL = None │ │ │ │ OPENAI_BASE_URL = None │ │ │ │ os = <module 'os' from │ │ │ │ '/usr/local/lib/python3.10/os.py'> │ │ │ │ rg = <module 'argilla' from │ │ │ │ '/usr/local/lib/python3.10/site-packages/argilla… │ │ │ │ SFT_TASK = 'supervised_fine_tuning' │ │ │ │ TEXTCAT_TASK = 'text_classification' │ │ │ │ TOKENIZER_ID = 'deepseek-ai/DeepSeek-R1' │ │ │ │ VLLM_BASE_URL = None │ │ │ │ warnings = <module 'warnings' from │ │ │ │ '/usr/local/lib/python3.10/warnings.py'> │ │ │ ╰──────────────────────────────────────────────────────────────────────────╯ │ ╰──────────────────────────────────────────────────────────────────────────────╯ ValueError: `HUGGINGFACE_BASE_URL` and `MODEL` cannot be set at the same time. Use a model id for serverless inference and a base URL dedicated to HF中国镜像站 Inference Endpoints.

Container logs: