Hi Navyata, thanks for the sharing. I have tried Llama3:70b, but too slow on Mac, how to safely remove the 70b model data? Shall I just delete the 39GB file? Is there other files need to be deleted together with it?
This content is very helpful, Thank!... I was also wondering if there is a way to talk to it continuously in a single thread like we do with Open AI's Assistance API.
doesnt work, nothing happens on ollama command line install step :(
Thank you for the excellent video. Complete and to the point!
Hi Navyata, thanks for the sharing.
I have tried Llama3:70b, but too slow on Mac, how to safely remove the 70b model data? Shall I just delete the 39GB file?
Is there other files need to be deleted together with it?
ollama rm [name of model]
ollama rm llama3
This content is very helpful, Thank!... I was also wondering if there is a way to talk to it continuously in a single thread like we do with Open AI's Assistance API.
So helpful!!
How I pull the Llama3.1:405 Parameters? Is it possible?
What is the exact value of unconditional love?
Thank you ** 10000