"model not found" and initialization hangs

Hi,

Why do some models work with vLLM serverless while others produce 'model not found' and workers hang on initialization? For example when I try to use this model with defaults it hangs: https://huggingface.co/AiCloser/Qwen2.5-32B-AGI
  • it does not matter if I input full url or just last part.
Was this page helpful?