Error while pulling Content Safety image (Payment required)

AI & Data Science NVIDIA NIM Access/Accounts
, , ,
1

After login into nvcr.io in docker and setting my api keys with the developer program, I tried to execute this command to deploy the Content safety model locally to try it, however, I got an error.

Command:

docker run --name nemo-guardrails -it --rm
–runtime=nvidia
–gpus device=0
-e NGC_API_KEY
-e NIM_SERVED_MODEL_NAME=“llama-3.1-nemoguard-8b-content-safety”
-e NIM_CUSTOM_MODEL_NAME=“llama-3.1-nemoguard-8b-content-safety”
-v “$LOCAL_NIM_CACHE:/opt/nim/.cache”
-u $(id -u)
-p 8000:8000
nvcr.io/nim/nvidia/llama-3.1-nemoguard-8b-content-safety:latest

Error:

docker: Error response from daemon: Head “https://nvcr.io/v2/nim/nvidia/llama-3.1-nemoguard-8b-content-safety/manifests/latest”: denied: Payment Required.

I tried also with the Topic Control model, and it worked just fine. What could be the issue here?

2

Hi @manuel55

The llama-3.1-nemoguard-8b-content-safety container is only available to those who have an active NVIDIA AI Enterprise subscription or trial. NVIDIA AI Enterprise

Best,

Sophie

3

Thank you! Didn’t know it was only available for those with Enterprise subscription.

4

Sure thing - I appreciate that it’s not the clearest to see that this needs an NVIDIA AI Enterprise subscription. We are working with the UX team to make this clearer.

In the mean time, you can see what subscriptions are reuqired by looking at the ‘Associated Prodcuts’ section of the model’s page on the NGC Catalog. Llama 3.1 NemoGuard 8B Content Safety | NVIDIA NGC

Best,

Sophie