runtime error

Exit code: 1. Reason: math = <module 'math' from │ │ │ │ '/usr/local/lib/python3.10/lib-dynloa… │ │ │ │ MODEL = 'meta-llama/Llama-3.1-8B-Instruct' │ │ │ │ MODEL_COMPLETION = 'deepseek-ai/DeepSeek-R1-Distill-Qwen… │ │ │ │ OLLAMA_BASE_URL = None │ │ │ │ OLLAMA_BASE_URL_COMPLETION = None │ │ │ │ OPENAI_BASE_URL = None │ │ │ │ OPENAI_BASE_URL_COMPLETION = None │ │ │ │ random = <module 'random' from │ │ │ │ '/usr/local/lib/python3.10/random.py'> │ │ │ │ TOKEN_INDEX = 1 │ │ │ │ TOKENIZER_ID = None │ │ │ │ TOKENIZER_ID_COMPLETION = None │ │ │ │ VLLM_BASE_URL = None │ │ │ │ VLLM_BASE_URL_COMPLETION = None │ │ │ ╰──────────────────────────────────────────────────────────────────────────╯ │ ╰──────────────────────────────────────────────────────────────────────────────╯ Exception: Error loading InferenceEndpointsLLM: 404 Client Error: Not Found for url: https://api-inference.huggingface.co/status/meta-llama/Llama-3.1-8B-Instruct (Request ID: Root=1-681e796c-3ffd104b771935736fd00014;f7168571-2f00-4253-9baf-62186f51cb59)

Container logs: