Hi
I am trying to deploy GPT- J model on the triton server but I am having no luck.
I have followed this blog post https://developer.nvidia.com/blog/deploying-gpt-j-and-t5-with-fastertransformer-and-triton-inference-server/
but this wget mystic.the-eye.eu/public/AI/GPT-J-6B/step_383500_slim.tar.zstd files doesn’t seem to exist if anyone who has set a triton server successfully can share any documentation that would be great.
Thanks