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 #10964] When API calls specify think:false, the output is unstable, and sometimes it includes thinking content. #69283

New Issue
Open
opened 2026-05-04 17:38:56 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-04 17:38:56 -05:00
Owner
Copy Link

Originally created by @hlstudio on GitHub (Jun 4, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10964

Originally assigned to: @drifkin on GitHub.

What is the issue?

Image

Image

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

0.9.0

Originally created by @hlstudio on GitHub (Jun 4, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10964 Originally assigned to: @drifkin on GitHub. ### What is the issue? ![Image](https://github.com/user-attachments/assets/63248349-5d48-4906-84e6-062d049a5c21) ![Image](https://github.com/user-attachments/assets/7e7c010b-74d4-4044-bc70-48c945e7639d) ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.9.0
GiteaMirror added the bug label 2026-05-04 17:38:56 -05:00
GiteaMirror commented 2026-05-04 17:38:59 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 8, 2025):

deepseek-r1 doesn't actually have a no-think mode, so the template tries to fake one for the model by inserting a blank think block at the end of the prompt. It looks like the model recognizes the opening <think>, since it doesn't output a new one, but not the closing </think>, since it writes one out.

Padding the think block with some text helps it recognize the trailing </think>. However, this reduces the quality of the output.

I think for deepseek-r1, the only really valid options for think are unset or true.

<!-- gh-comment-id:2954232406 --> @rick-github commented on GitHub (Jun 8, 2025): deepseek-r1 doesn't actually have a no-think mode, so the template tries to fake one for the model by inserting a blank think block at the end of the prompt. It looks like the model recognizes the opening `<think>`, since it doesn't output a new one, but not the closing `</think>`, since it writes one out. Padding the think block with some text helps it recognize the trailing `</think>`. However, this reduces the quality of the output. I think for deepseek-r1, the only really valid options for `think` are unset or `true`.
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#69283
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?