github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9859] creating ollama custom model using modelfile inside docker #6456

New Issue
Closed
opened 2026-04-12 18:01:05 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 18:01:05 -05:00
Owner
Copy Link

Originally created by @babu-kandyala on GitHub (Mar 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9859

What is the issue?

i am trying to build docker image with custom model using modelfile(with param's) with ollama/ollama:0.6.0 as base image. below is the Dockerfile

Using base image

FROM ollama/ollama:0.6.0

Adding an unprivileged user

RUN groupadd --gid 10001 ollama &&
useradd --uid 10001 --gid ollama --shell /bin/bash --create-home ollama

Change the ownership to ollama and provide necessary permissions

RUN chown -R ollama:ollama /bin/ollama && chmod 755 /bin/ollama

COPY modelfile modelfile

Create custom model

RUN ollama -v
RUN ollama serve &
RUN ollama run llama3.2
RUN ollama create ollama_custom -f modelfile

Make port 11434 available to the world outside this container

EXPOSE 11434

Run with no admin user

USER 10001

Run the custom model

CMD ["ollama", "run", "my_custom_model", "what is 2+2=? and say jonny jonny yes papa poem"]

docker build is failing with below error

#11 ERROR: process "/bin/sh -c ollama run llama3.2" did not complete successfully: exit code: 1

[7/8] RUN ollama run llama3.2:
0.174 Error: could not connect to ollama app, is it running?

Dockerfile:15

13 | RUN ollama -v
14 | RUN ollama serve &
15 | >>> RUN ollama run llama3.2
16 | RUN ollama create ollama_custom -f modelfile
17 |

ERROR: failed to solve: process "/bin/sh -c ollama run llama3.2" did not complete successfully: exit code: 1

Relevant log output

OS

Docker

GPU

AMD

CPU

AMD

Ollama version

0.6.0

Originally created by @babu-kandyala on GitHub (Mar 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9859 ### What is the issue? i am trying to build docker image with custom model using modelfile(with param's) with ollama/ollama:0.6.0 as base image. below is the Dockerfile # Using base image FROM ollama/ollama:0.6.0 # Adding an unprivileged user RUN groupadd --gid 10001 ollama && \ useradd --uid 10001 --gid ollama --shell /bin/bash --create-home ollama # Change the ownership to ollama and provide necessary permissions RUN chown -R ollama:ollama /bin/ollama && chmod 755 /bin/ollama COPY modelfile modelfile # Create custom model RUN ollama -v RUN ollama serve & RUN ollama run llama3.2 RUN ollama create ollama_custom -f modelfile # Make port 11434 available to the world outside this container EXPOSE 11434 # Run with no admin user USER 10001 # Run the custom model CMD ["ollama", "run", "my_custom_model", "what is 2+2=? and say jonny jonny yes papa poem"] docker build is failing with below error #11 ERROR: process "/bin/sh -c ollama run llama3.2" did not complete successfully: exit code: 1 ------ > [7/8] RUN ollama run llama3.2: 0.174 Error: could not connect to ollama app, is it running? ------ Dockerfile:15 -------------------- 13 | RUN ollama -v 14 | RUN ollama serve & 15 | >>> RUN ollama run llama3.2 16 | RUN ollama create ollama_custom -f modelfile 17 | -------------------- ERROR: failed to solve: process "/bin/sh -c ollama run llama3.2" did not complete successfully: exit code: 1 ### Relevant log output ```shell ``` ### OS Docker ### GPU AMD ### CPU AMD ### Ollama version 0.6.0
GiteaMirror added the question label 2026-04-12 18:01:05 -05:00
GiteaMirror commented 2026-04-12 18:01:06 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 18, 2025):

# Create custom model
RUN ollama serve & server=$! ; sleep 2 ; ollama pull llama3.2 ; ollama create ollama_custom -f modelfile ; kill $server
# Run the custom model
ENTRYPOINT [ "/bin/bash", "-c", "(sleep 2 ; ollama run ollama_custom '') & exec /bin/ollama $0" ]
CMD [ "serve" ]
<!-- gh-comment-id:2733976464 --> @rick-github commented on GitHub (Mar 18, 2025): ```dockerfile # Create custom model RUN ollama serve & server=$! ; sleep 2 ; ollama pull llama3.2 ; ollama create ollama_custom -f modelfile ; kill $server # Run the custom model ENTRYPOINT [ "/bin/bash", "-c", "(sleep 2 ; ollama run ollama_custom '') & exec /bin/ollama $0" ] CMD [ "serve" ] ```
GiteaMirror commented 2026-04-12 18:01:08 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 18, 2025):

Going to close this as answered (thanks @rick-github !)

<!-- gh-comment-id:2734624817 --> @pdevine commented on GitHub (Mar 18, 2025): Going to close this as answered (thanks @rick-github !)
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 question
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#6456
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?