Yes I got it from the provided link only
Did you get your API key by clicking the Get API Key on this page?
Then run the command on your side by referring to the page.
$ docker login nvcr.io
Username: $oauthtoken
Password: <YOUR_API_KEY>
export NGC_API_KEY=<YOUR_API_KEY>
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p "$LOCAL_NIM_CACHE"
docker run -it --rm \
...
Yes, We tried the way you told above but getting the below error:
Exception: error sending request for url (
https://api.ngc.nvidia.com/v2/org/nim/team/meta/models/llama3-8b-instruct/hf/files)
Can you please look into this on priority.
Could you try to modify this to nvcr.io/nim/meta/llama3-8b-instruct:1.0.0 and run?
We tried that as well but it is giving same error.
We Followed Getting Started - NVIDIA Docs document step by step (both API catalog and NGC approach) to launch NVIDIA NIM (llama3-8b-instruct) for LLMs locally but facing below error:
Can you please look into this issue on priority
Could you file a new topic about the new error to our NIM forum?
But error are related to VIA Microservices only.
Can you please suggest solution here in the same loop, So that it will be easy to track
I mean you can file a new topic in the NIM forum just about this issue #27.
This seems to be a problem when you deploy the NIM locally. Problems about NIM will be addressed more quickly in the NIM forum.
How to solve the Huggingface error problem？
Sorry for late reply. Have you tried this method we attached on this topic before? You can also file a new topic about your issue.
@rawnak.kumar Can you refer to Air Gap Deployment for NVIDIA NIM for LLMs - NVIDIA Docs to have a try?
Let me give it a try.
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.