In this video I show you Ollama to work with Large Language Models on the Radxa Rock 5B with 16GB RAM and the Rockchip RK3588.
You can use Ollama as a chatbot, like ChatGPT, but with Llava you can also use it for image recognition.
https://github.com/ollama/ollama
curl -fsSL https://ollama.com/install.sh | sh
Example commands:
ollama run llama2:13b
ollama run llama2 "Summarize this file: $(cat README.md)"
https://linuxconfig.org/how-to-extrac...
00:00 Intro
00:30 Ollama Github
03:00 Model File Installation Error
04:00 Running llama2:13b
15:22 Result of the 13B Model File
15:45 Running llama2 (7b)
21:20 Result of the 7B Model File
22:30 Hallucination?
25:25 LlaVA Image Recognition
29:50 Summarize text with Ollama
34:10 Extract text from PDF
35:35 LlaVA Result
Used documents:
https://en.wikibooks.org/wiki/Knowing...
https://en.wikibooks.org/wiki/FOSS_A_...
If this video was helpful, please like, comment and subscribe!
Bluesky: https://bsky.app/profile/livinglinux....
Twitter: / livinglinux
#Radxa #Rock5 #rockchip #RK3588 #ai #ollama