Can anyone please provide me step by step instructions on how to run llamaspeak on a Jetson Orin nano Super 8gig with jetpack 6.2 fresh setup using the sdkmanager, starting from logging in to your home directory?
I have watched the videos and read the readme files and can’t understand what the steps are to actually make it work.
Please don’t think I am stupid, a complete example would go a long way to help me get over hump I hope.
Thanks in advance to anyone that steps up to try and help me.
Hi,
We have a llamaspeak tutorial here:
As you are using 8GB device, please make sure you have optimized the memory with the tutorial below:
Thanks.
Well I thank you for the reply but the tutorial is not that complete for someone new to this technology. A step by step guide would be much better. More like the second post you referenced in your reply.
Hi,
You will need to start the Riva server first.
Then launch the nano_llm container with jetson_container.
Thanks.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.