docker model package doesn't inherent model features ( no vision decoding )
Open
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:
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
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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