github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7052] Capability checking does not consider custom templates #30237

New Issue
Open
opened 2026-04-22 09:45:56 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 09:45:56 -05:00
Owner
Copy Link

Originally created by @kyRobot on GitHub (Oct 1, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7052

What is the issue?

When sending a completion request to a model that supports FIM tasks - e.g Qwen 2.5 Coder 7B base - Ollama rejects the request because the "model does not support insert".

Passing raw with the necessary prompt format to the model does work for completion, so the issue is not with the model, it is with Ollamas acceptance of the non-raw prompt.

I found the issue is that the Modelfile template does not contain {{.Suffix}} since the instruct version of the same model, which does include suffix does work for completions, in raw mode and otherwise.

Passing a custom template in the request to the base mode however does not work. Ollama gives the same "model does not support insert" error.

The server code shows that only the modelfile template is considered for compatability checking.

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.3.12

Originally created by @kyRobot on GitHub (Oct 1, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7052 ### What is the issue? When sending a completion request to a model that supports FIM tasks - e.g Qwen 2.5 Coder 7B base - Ollama rejects the request because the "model does not support insert". Passing `raw` with the necessary prompt format to the model does work for completion, so the issue is not with the model, it is with Ollamas acceptance of the non-raw prompt. I found the issue is that the Modelfile template does not contain `{{.Suffix}}` since the instruct version of the same model, which does include suffix does work for completions, in raw mode and otherwise. Passing a custom template in the request to the base mode however does not work. Ollama gives the same "model does not support insert" error. The server code shows that only the modelfile template is considered for compatability checking. ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.3.12
GiteaMirror added the bug label 2026-04-22 09:45:57 -05:00
GiteaMirror commented 2026-04-22 09:45:57 -05:00
Author
Owner
Copy Link

@kyRobot commented on GitHub (Oct 1, 2024):

Opened PR #7026 to resolve this issue. Awaiting review and merge

<!-- gh-comment-id:2384562217 --> @kyRobot commented on GitHub (Oct 1, 2024): Opened PR #7026 to resolve this issue. Awaiting review and merge
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 bug
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#30237
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?