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

[PR #15859] Improve error message for unsupported model architectures with actionable guidance #77626

New Issue
Open
opened 2026-05-05 10:17:59 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 10:17:59 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/15859
Author: @gotnochill815-web
Created: 4/28/2026
Status: 🔄 Open

Base: main ← Head: improve-arch-error-guidance

📝 Commits (1)

  • 280b288 Improve unsupported model architecture error message with actionable guidance

📊 Changes

1 file changed (+1 additions, -1 deletions)

View changed files

📝 llama/llama.cpp/src/llama-model.cpp (+1 -1)

📄 Description

Summary

Improves the error message shown when loading unsupported model architectures.

Changes

  • Includes the detected architecture name in the error message
  • Clarifies that the architecture may exist in upstream llama.cpp but is not yet supported in the current Ollama version
  • Provides actionable suggestions (update Ollama or check backend compatibility)

Motivation

Users encountering errors like unknown model architecture may misinterpret the issue as a corrupted model or configuration problem.

In cases like #15824, the real issue is that the architecture (e.g., glm-dsa) exists upstream but has not yet been integrated into Ollama.

This change improves clarity and reduces confusion.

Example

Before:

unknown model architecture: 'glm-dsa'

After:

unsupported model architecture: 'glm-dsa'
This architecture may exist in upstream llama.cpp but is not yet supported in this Ollama version.
Try:
- updating Ollama
- checking if the model requires a newer llama.cpp backend

Related

Closes confusion in #15824

🔄 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/15859 **Author:** [@gotnochill815-web](https://github.com/gotnochill815-web) **Created:** 4/28/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `improve-arch-error-guidance` --- ### 📝 Commits (1) - [`280b288`](https://github.com/ollama/ollama/commit/280b2885ba7bc0c7763b0d201a6652d4c0c3aa24) Improve unsupported model architecture error message with actionable guidance ### 📊 Changes **1 file changed** (+1 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `llama/llama.cpp/src/llama-model.cpp` (+1 -1) </details> ### 📄 Description ## Summary Improves the error message shown when loading unsupported model architectures. ## Changes * Includes the detected architecture name in the error message * Clarifies that the architecture may exist in upstream llama.cpp but is not yet supported in the current Ollama version * Provides actionable suggestions (update Ollama or check backend compatibility) ## Motivation Users encountering errors like `unknown model architecture` may misinterpret the issue as a corrupted model or configuration problem. In cases like #15824, the real issue is that the architecture (e.g., `glm-dsa`) exists upstream but has not yet been integrated into Ollama. This change improves clarity and reduces confusion. ## Example Before: ``` unknown model architecture: 'glm-dsa' ``` After: ``` unsupported model architecture: 'glm-dsa' This architecture may exist in upstream llama.cpp but is not yet supported in this Ollama version. Try: - updating Ollama - checking if the model requires a newer llama.cpp backend ``` ## Related Closes confusion in #15824 --- <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 2026-05-05 10:17:59 -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#77626
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?