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 #10891] Qwen3 Template error after first message #53672

New Issue
Closed
opened 2026-04-29 04:27:10 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-29 04:27:10 -05:00
Owner
Copy Link

Originally created by @Ctrl-Alt-Calvin on GitHub (May 29, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10891

What is the issue?

When running any new Qwen3 model, I get a template error after sending a second message after the first message. No such issue when trying llama3.1 model. Here is an example of the error:

hey!

Okay, the user said, "Hey!" so I need to respond in a friendly and helpful way. Let me start by acknowledging
their greeting. Maybe say something like, "Hey! How can I help you today?" That's a good opening. I should keep it
simple and positive. I don't want to make it too formal, so just a friendly reply. Also, I should make sure to
offer assistance in case they have any questions or need support. Let me check if there's any specific context I
should consider, but since the user didn't mention anything, it's best to keep it general. Alright, time to put it
all together into a natural response.

Hey! How can I help you today? 😊 What can I do for you?

howdy!
Error: template: :42:11: executing "" at <.Thinking>: can't evaluate field Thinking in type *api.Message

Relevant log output

OS

Windows, Linux

GPU

Nvidia

CPU

No response

Ollama version

0.8.0

Originally created by @Ctrl-Alt-Calvin on GitHub (May 29, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10891 ### What is the issue? When running any new Qwen3 model, I get a template error after sending a second message after the first message. No such issue when trying llama3.1 model. Here is an example of the error: >>> hey! <think> Okay, the user said, "Hey!" so I need to respond in a friendly and helpful way. Let me start by acknowledging their greeting. Maybe say something like, "Hey! How can I help you today?" That's a good opening. I should keep it simple and positive. I don't want to make it too formal, so just a friendly reply. Also, I should make sure to offer assistance in case they have any questions or need support. Let me check if there's any specific context I should consider, but since the user didn't mention anything, it's best to keep it general. Alright, time to put it all together into a natural response. </think> Hey! How can I help you today? 😊 What can I do for you? >>> howdy! Error: template: :42:11: executing "" at <.Thinking>: can't evaluate field Thinking in type *api.Message ### Relevant log output ```shell ``` ### OS Windows, Linux ### GPU Nvidia ### CPU _No response_ ### Ollama version 0.8.0
GiteaMirror added the bug label 2026-04-29 04:27:10 -05:00
GiteaMirror commented 2026-04-29 04:27:12 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 29, 2025):

It looks like some of the models have had their template updated in preparation for https://github.com/ollama/ollama/pull/10584. But that hasn't been integrated yet, so the template parsing fails. @drifkin

<!-- gh-comment-id:2917943492 --> @rick-github commented on GitHub (May 29, 2025): It looks like some of the models have had their template updated in preparation for https://github.com/ollama/ollama/pull/10584. But that hasn't been integrated yet, so the template parsing fails. @drifkin
GiteaMirror commented 2026-04-29 04:27:12 -05:00
Author
Owner
Copy Link

@drifkin commented on GitHub (May 29, 2025):

I've reverted the template changes temporarily, they were intended to be backwards compatible. @Ctrl-Alt-Calvin could you help me repro? Did you run this using the CLI? If so, interactive or not? Or did you use the API?

<!-- gh-comment-id:2917958320 --> @drifkin commented on GitHub (May 29, 2025): I've reverted the template changes temporarily, they were intended to be backwards compatible. @Ctrl-Alt-Calvin could you help me repro? Did you run this using the CLI? If so, interactive or not? Or did you use the API?
GiteaMirror commented 2026-04-29 04:27:13 -05:00
Author
Owner
Copy Link

@drifkin commented on GitHub (May 29, 2025):

oops sorry, was able to repro with a simple chat on the CLI, I was testing it wrong. Fix incoming! Thanks for reporting!

<!-- gh-comment-id:2917977263 --> @drifkin commented on GitHub (May 29, 2025): oops sorry, was able to repro with a simple chat on the CLI, I was testing it wrong. Fix incoming! Thanks for reporting!
GiteaMirror commented 2026-04-29 04:27:13 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 29, 2025):

This should be fixed now. Thanks for the issue!

<!-- gh-comment-id:2918074902 --> @jmorganca commented on GitHub (May 29, 2025): This should be fixed now. Thanks for the issue!
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#53672
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?