meta-llama

/

Meta-Llama-3.1-405B-FP8

like 94

was testing this out last week and now im getting errors:The model meta-llama/Meta-Llama-3.1-405B-FP8 is too large to be loaded automatically (162GB > 10GB). Please use Spaces (https://huggingface.co/spaces) or Inference Endpoints (https://huggingface.co/inference-endpoints)."}
are pro users no longer able to run inference on these? it was the only reason i upgraded to pro.