Finally, I got the time to install the Llama GPT bot, how hard can it be? what are the challenges to set it up? Let’s find out.
My Gears:
nVidia 4070 TI:
AMD 9 5900x:
laptop:
keyboard:
mouse:
CPU:
camera:
lens:
home server 1:
home server 2:
home server 3:
Links:
Llama GPT setup link:
Timecode
0:00 – What is LlamaGPT? Why is it popular
0:21 – What do you need to set up the offline ChatGPT with unlimited questions?
0:38 – Preparation: Ubuntu Linux
0:51 – Install Ubuntu and nVidia GPU driver on Linux
1:18 – Install Docker desktop on Ubuntu Linux
1:34 – How to solve Docker Desktop unmet dependencies docker-ce-cli
2:02 – Let’s setup llama gpt using umbrel repo
2:26 – how long does it take to setup LLAMA GPT? (a quick reference)
2:54 – Llama gpt UI connection was reset
3:07 – how to solve nvidia-container-cli error libnvidia-ml.so.1 cannot open shared object no such file or directory
3:30 – Use docker-ce to solve the LLAMA GPT libnvidia issue.
4:14 – try Llama GPT with docker-ce
4:57 – docker desktop vs docker-ce on linux
5:13 – install Llama gpt
5:38 – Llama GPT docker cannot select device driver “nVidia” with compatibility
6:05 – Llama GPT working on live
7:26 – What to look out for when setting up Llama GPT server with umbrel github
[ad_2]
source
-
-
-
-
