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 #4591] Phi-3 Vision #64919

New Issue
Closed
opened 2026-05-03 19:16:28 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-05-03 19:16:28 -05:00
Owner
Copy Link

Originally created by @ddpasa on GitHub (May 23, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4591

Phi-3 is already supported, so I hope this should not be too difficult:

https://huggingface.co/microsoft/Phi-3-vision-128k-instruct

Originally created by @ddpasa on GitHub (May 23, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4591 Phi-3 is already supported, so I hope this should not be too difficult: https://huggingface.co/microsoft/Phi-3-vision-128k-instruct
GiteaMirror added the model label 2026-05-03 19:16:28 -05:00
GiteaMirror commented 2026-05-03 19:16:31 -05:00
Author
Owner
Copy Link

@coder543 commented on GitHub (May 23, 2024):

https://github.com/ollama/ollama/issues/4560

<!-- gh-comment-id:2127336544 --> @coder543 commented on GitHub (May 23, 2024): https://github.com/ollama/ollama/issues/4560
GiteaMirror commented 2026-05-03 19:16:31 -05:00
Author
Owner
Copy Link

@Replikate648 commented on GitHub (May 23, 2024):

Is Phi-3-vision still have to be added in ollama?

<!-- gh-comment-id:2127904530 --> @Replikate648 commented on GitHub (May 23, 2024): Is Phi-3-vision still have to be added in ollama?
GiteaMirror commented 2026-05-03 19:16:33 -05:00
Author
Owner
Copy Link

@TadayukiOkada commented on GitHub (May 24, 2024):

https://github.com/ggerganov/llama.cpp/issues/7444

<!-- gh-comment-id:2128474023 --> @TadayukiOkada commented on GitHub (May 24, 2024): https://github.com/ggerganov/llama.cpp/issues/7444
GiteaMirror commented 2026-05-03 19:16:35 -05:00
Author
Owner
Copy Link

@HaoHoo commented on GitHub (May 28, 2024):

Looks like that llama.cpp convert HF to GGUF code can't support Phi3V yet.

<!-- gh-comment-id:2134561936 --> @HaoHoo commented on GitHub (May 28, 2024): Looks like that llama.cpp convert HF to GGUF code can't support Phi3V yet.
GiteaMirror commented 2026-05-03 19:16:38 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jun 5, 2024):

Going to close this as a dupe.

<!-- gh-comment-id:2150920982 --> @pdevine commented on GitHub (Jun 5, 2024): Going to close this as a dupe.
GiteaMirror commented 2026-05-03 19:16:39 -05:00
Author
Owner
Copy Link

@levicki commented on GitHub (Sep 15, 2024):

@pdevine Can you please clarify whether Phi3-vision is supported or not? If yes, what is the proper template for it?

<!-- gh-comment-id:2351585588 --> @levicki commented on GitHub (Sep 15, 2024): @pdevine Can you please clarify whether Phi3-vision is supported or not? If yes, what is the proper template for it?
GiteaMirror commented 2026-05-03 19:16:40 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 15, 2024):

@levicki Unfortunately not yet. The dupe was to track it in #4560

<!-- gh-comment-id:2351614611 --> @pdevine commented on GitHub (Sep 15, 2024): @levicki Unfortunately not yet. The dupe was to track it in #4560
GiteaMirror commented 2026-05-03 19:16:42 -05:00
Author
Owner
Copy Link

@levicki commented on GitHub (Sep 15, 2024):

@levicki Unfortunately not yet. The dupe was to track it in #4560

@pdevine

Thanks for the clarification. I am confused as to what the problem is with supporting that model? There's also a newer version (3.5) that came out in the meantime. Didn't llama.cpp already add support for it? Or is there perhaps some other issue with it?

Edit: Nevermind, found what's the problem here.

<!-- gh-comment-id:2351766139 --> @levicki commented on GitHub (Sep 15, 2024): > @levicki Unfortunately not yet. The dupe was to track it in #4560 @pdevine Thanks for the clarification. I am confused as to what the problem is with supporting that model? There's also a newer version (3.5) that came out in the meantime. Didn't llama.cpp already add support for it? Or is there perhaps some other issue with it? Edit: Nevermind, found what's the problem [here](https://github.com/ggerganov/llama.cpp/pull/7705).
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 model
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#64919
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?