It is easy to install in a docker container but i can’t do
https://hub.docker.com/r/ollama/ollama
Can anyone help.
What have you tried?
What did you expect to happen?
What actually happened?
2 Likes
Everything goes smoothly but the issue happend that
docker exec -it ollama ollama run llama2
It said no contrainer found.
But if i run
Docker run -it ollama
It run but does not show any prompt to install the model can you help i think if you can manage to install that on your system you can help me. Figure this out.
docker container start ollama
docker container list -a
docker exec ...
1 Like
Done thanks.
1 Like
Btw anyone wants to run llama locally. Try this
Until unless fedora give an ai.
If i use podman instead of docker that does not work
This works for me on Fedora 40:
podman run -d -v ollama:/root/.ollama \
-p 11434:11434 --name ollama ollama/ollama
podman container start ollama
podman exec -it ollama ollama run llama2
Probably you are doing something wrong.
2 Likes
I have deleted all the images and start new and now i run and i am also surprised to see it works.
If you don’t have a lot of ram you can use a smaller option like gemma:2b just change the last llama2 with this.
1 Like
Can’t install this GitHub - getumbrel/llama-gpt: A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
./run.sh
I find an error that -f is not a flag how to fix it.
This is how it should work:
sudo dnf -y install podman-docker podman-compose
sudo setenforce 0
git clone https://github.com/getumbrel/llama-gpt.git
cd llama-gpt
./run.sh --model 7b
However, the deployment takes quite a lot of time.
I will try and let you know.
This tool makes it easy if it helps:
I am using brew to simplify things.
brew install ollama