docker / docker/model-runner

docker model package doesn't inherent model features ( no vision decoding )

Open
#963 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Go
Stars
651
Forks
155
PR merge metrics
No merged PRs in 30d

Description

original model from dockerhub:

Image
docker model rm gemma4:12B_256k
docker model package --from ai/gemma4:12B --context-size 262144 gemma4:12B_256k
docker model run gemma4:12B_256k ~/Bilder/Screenshots/axu_hochkant.png whats on the screenshot ?
docker model run gemma4:12B_256k who are you ?on the screenshot ?

^^ as expected the original model starts to describe the image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by running the reported docker model rm, docker model package, and docker model run commands with ai/gemma4:12B and the image prompt. Compare the packaged model's behavior with the original model; done means the packaged model preserves vision decoding and answers the screenshot question.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker
Domain
ai
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
50/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.