unsloth/qwen3-8b hangs when pulling safetensors from HF
#2
by
gradientrouting-spar
- opened
When I am trying to pull from HF e.g. with vllm serve "unsloth/Qwen3-8B" it hangs with
INFO 06-10 18:17:26 [weight_utils.py:291] Using model weights format ['*.safetensors']
forever on 3 different machines?
Anyone else experiencing this