runtime error

Exit code: 1. Reason: Downloading model (this can take a while)... /usr/local/lib/python3.10/site-packages/huggingface_hub/file_download.py:945: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. warnings.warn( Qwen3-Embedding-0.6B-Q8_0.gguf: 0%| | 0.00/639M [00:00<?, ?B/s] Qwen3-Embedding-0.6B-Q8_0.gguf: 9%|▉ | 60.2M/639M [00:01<00:13, 44.0MB/s] Qwen3-Embedding-0.6B-Q8_0.gguf: 100%|██████████| 639M/639M [00:02<00:00, 277MB/s]  Qwen3-Embedding-0.6B-Q8_0.gguf: 100%|██████████| 639M/639M [00:02<00:00, 241MB/s] Downloaded to: Qwen3-Embedding-0.6B-Q8_0.gguf Building llama.cpp (may take many minutes)... >>> build_llama.sh starting at Thu Jan 22 15:33:14 CET 2026 Cloning into 'llama.cpp'... remote: Internal Server Error fatal: unable to access 'https://github.com/ggml-org/llama.cpp/': The requested URL returned error: 500 Build failed with code 128 Failed to build llama.cpp

Container logs: