github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 06:31:50 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7401] Configure docker image to start with some models installed #4707

New Issue
Closed
opened 2026-04-12 15:38:59 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 15:38:59 -05:00
Owner
Copy Link

Originally created by @fnacarellidev on GitHub (Oct 28, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7401

I think it would be very nice if we had an option to install some models on the build stage of the ollama docker image, right now I have 2 workarounds to emulate this behaviour:

  1. Have an init container that talks to the ollama container and installs the models, not very good because I can't cache that, so everytime I restart the kubernetes environment it has to reinstall each model, which might take long depending on the environment.

FROM ollama/ollama

RUN nohup bash -c "ollama serve &" && wait4x http http://127.0.0.1:11434 && ollama pull llava && ollama pull llama3

However the 2nd option is not working very well, when I install the models in that way every request take a lot of time to finish, and sometimes it doesn't finishes, it simply hangs, not sure if there's something wrong with the logic, I copied from the #957 issue.

Originally created by @fnacarellidev on GitHub (Oct 28, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7401 I think it would be very nice if we had an option to install some models on the build stage of the ollama docker image, right now I have 2 workarounds to emulate this behaviour: 1. Have an init container that talks to the ollama container and installs the models, not very good because I can't cache that, so everytime I restart the kubernetes environment it has to reinstall each model, which might take long depending on the environment. 2. ```dockerfile FROM ollama/ollama RUN nohup bash -c "ollama serve &" && wait4x http http://127.0.0.1:11434 && ollama pull llava && ollama pull llama3 ``` However the 2nd option is not working very well, when I install the models in that way every request take a lot of time to finish, and sometimes it doesn't finishes, it simply hangs, not sure if there's something wrong with the logic, I copied from the #957 issue.
GiteaMirror added the feature request label 2026-04-12 15:38:59 -05:00
GiteaMirror commented 2026-04-12 15:39:01 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 28, 2024):

https://github.com/ollama/ollama/issues/7046#issuecomment-2383792234

<!-- gh-comment-id:2442145306 --> @rick-github commented on GitHub (Oct 28, 2024): https://github.com/ollama/ollama/issues/7046#issuecomment-2383792234
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#4707
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?