github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3477] Support CLIP in LLaVA to provide services externally #64179

New Issue
Open
opened 2026-05-03 16:28:34 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-03 16:28:34 -05:00
Owner
Copy Link

Originally created by @Andiedie on GitHub (Apr 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3477

What are you trying to do?

I am new to ollama (including llama.cpp, of course), so my questions may be a bit silly.

My use case is to serve both CLIP and LLaVA (which combines clip and mistral) at the same time.

LLaVA can run perfectly on ollama. But I need to open another service for CLIP.

What I want to ask is

  1. Can ollama support the CLIP embedding interface? The current embedding interface seems to only support text.
  2. Since the frozen CLIP included in LLaVA running on ollama, can it be directly reused instead of loading two copies in memory?

How should we solve this?

No response

What is the impact of not solving this?

No response

Anything else?

No response

Originally created by @Andiedie on GitHub (Apr 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3477 ### What are you trying to do? I am new to ollama (including llama.cpp, of course), so my questions may be a bit silly. My use case is to serve both CLIP and LLaVA (which combines clip and mistral) at the same time. LLaVA can run perfectly on ollama. But I need to open another service for CLIP. What I want to ask is 1. Can ollama support the CLIP embedding interface? The current embedding interface seems to only support text. 2. Since the frozen CLIP included in LLaVA running on ollama, can it be directly reused instead of loading two copies in memory? ### How should we solve this? _No response_ ### What is the impact of not solving this? _No response_ ### Anything else? _No response_
GiteaMirror commented 2026-05-03 16:28:35 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Apr 4, 2024):

Hi @Andiedie
LLava uses CLIP internally to understand images, but you can't directly ask CLIP questions within LLava.<
There's currently no way to use CLIP independently from LLava.

Here are some options:

You could try to build a new model for Ollama from the Hugging face code of CLIP. Or someone could have done it and could publish it.

<!-- gh-comment-id:2035932858 --> @igorschlum commented on GitHub (Apr 4, 2024): Hi @Andiedie LLava uses CLIP internally to understand images, but you can't directly ask CLIP questions within LLava.< There's currently no way to use CLIP independently from LLava. Here are some options: You could try to build a new model for Ollama from the Hugging face code of CLIP. Or someone could have done it and could publish it.
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#64179
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?