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

[PR #10025] [CLOSED] Fix schema in minicpmv #23660

New Issue
Closed
opened 2026-04-19 17:08:05 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-19 17:08:05 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/10025
Author: @tc-mb
Created: 3/28/2025
Status: ❌ Closed

Base: main ← Head: fix-schema-in-minicpmv

📝 Commits (2)

📊 Changes

2 files changed (+74 additions, -2 deletions)

View changed files

📝 llama/llama.go (+12 -0)
📝 runner/llamarunner/runner.go (+62 -2)

📄 Description

I submitted a PR that included omni model capabilities and asked me to modify it with the new engine. I am still modifying it.

https://github.com/ollama/ollama/pull/9672

But the previous PR also included some accuracy fixes for the existing minicpm-v model. I want to merge one of the fixed parts into the old engine first.

Users can use the previous code directly without any difference.

Before the fix, if a user recognizes a picture, because the schema is incorrect. It cannot handle large pictures well, especially it will say that the picture is in the form of mosaics.

After the fix, it should be able to correctly understand large pictures and be consistent with our training.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/10025 **Author:** [@tc-mb](https://github.com/tc-mb) **Created:** 3/28/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `fix-schema-in-minicpmv` --- ### 📝 Commits (2) - [`6a69927`](https://github.com/ollama/ollama/commit/6a699274516edc3af70a33612157033a85297a3c) fix schema in minicpmv - [`11a3c73`](https://github.com/ollama/ollama/commit/11a3c733e137731e2daf97bbdf3c9233bdab288f) Merge pull request #25 from tc-mb/main ### 📊 Changes **2 files changed** (+74 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `llama/llama.go` (+12 -0) 📝 `runner/llamarunner/runner.go` (+62 -2) </details> ### 📄 Description I submitted a PR that included omni model capabilities and asked me to modify it with the new engine. I am still modifying it. https://github.com/ollama/ollama/pull/9672 But the previous PR also included some accuracy fixes for the existing minicpm-v model. I want to merge one of the fixed parts into the old engine first. Users can use the previous code directly without any difference. Before the fix, if a user recognizes a picture, because the schema is incorrect. It cannot handle large pictures well, especially it will say that the picture is in the form of mosaics. After the fix, it should be able to correctly understand large pictures and be consistent with our training. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-19 17:08:05 -05:00
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 pull-request
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#23660
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?