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 #1772] Metadata field for multimodal models #26777

New Issue
Closed
opened 2026-04-22 03:22:44 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 03:22:44 -05:00
Owner
Copy Link

Originally created by @shreyaskarnik on GitHub (Jan 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/1772

Would it be possible to add some metadata to the model indicating that it is multimodal? This will help to select the right model in applications that are built on top of the API to support multimodal architecture. I believe this will also help to search through models at https://ollama.ai/library and filter based on multimodal support.

Originally created by @shreyaskarnik on GitHub (Jan 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/1772 Would it be possible to add some metadata to the model indicating that it is multimodal? This will help to select the right model in applications that are built on top of the API to support multimodal architecture. I believe this will also help to search through models at https://ollama.ai/library and filter based on multimodal support.
GiteaMirror commented 2026-04-22 03:22:45 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jan 4, 2024):

This is possible already through the API by using the /api/show endpoint and looking through .details.families. An example with curl:

curl localhost:11434/api/show -X POST -d '{"name": "llava"}' | jq ".details.families"

It should output:

[
  "llama",
  "clip"
]

It shows the two families which the model uses (i.e. the "multimodal" part), namely the "llama" model family for that chat portion, and the "clip" family which is used for converting images into text descriptions.

Hopefully that helps! I'm going to close the issue, but feel free to keep commenting on it/re-open it.

<!-- gh-comment-id:1876138025 --> @pdevine commented on GitHub (Jan 4, 2024): This is possible already through the API by using the `/api/show` endpoint and looking through `.details.families`. An example with curl: ``` curl localhost:11434/api/show -X POST -d '{"name": "llava"}' | jq ".details.families" ``` It should output: ``` [ "llama", "clip" ] ``` It shows the two families which the model uses (i.e. the "multimodal" part), namely the "llama" model family for that chat portion, and the "clip" family which is used for converting images into text descriptions. Hopefully that helps! I'm going to close the issue, but feel free to keep commenting on it/re-open it.
GiteaMirror commented 2026-04-22 03:22:46 -05:00
Author
Owner
Copy Link

@shreyaskarnik commented on GitHub (Jan 4, 2024):

@pdevine thanks for the clarification I was using the clip selector to make the appropriate selection of model. Thanks for confirming that it is the way to go. On the https://ollama.ai/library page will there be a option to select only multimodal models in the future?

<!-- gh-comment-id:1876143666 --> @shreyaskarnik commented on GitHub (Jan 4, 2024): @pdevine thanks for the clarification I was using the clip selector to make the appropriate selection of model. Thanks for confirming that it is the way to go. On the https://ollama.ai/library page will there be a option to select only multimodal models in the future?
GiteaMirror commented 2026-04-22 03:22:46 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jan 4, 2024):

Sounds like a really good addition.

<!-- gh-comment-id:1876190176 --> @pdevine commented on GitHub (Jan 4, 2024): Sounds like a really good addition.
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
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#26777
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?