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 #13168] deepseek-ocr模型对话重复 #70765

New Issue
Closed
opened 2026-05-04 22:53:04 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-04 22:53:04 -05:00
Owner
Copy Link

Originally created by @Adam-xuya on GitHub (Nov 20, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13168

What is the issue?

发送消息，不管是啥，回复的消息始终无限重复

Image Image

Relevant log output

OS

mac os 26.1

GPU

No response

Apple M1 Max

No response

Ollama version

0.13

Originally created by @Adam-xuya on GitHub (Nov 20, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13168 ### What is the issue? 发送消息，不管是啥，回复的消息始终无限重复 <img width="1500" height="1472" alt="Image" src="https://github.com/user-attachments/assets/2ecc82a4-acc2-4cd1-bd3b-1390a6d3a45f" /> <img width="2642" height="470" alt="Image" src="https://github.com/user-attachments/assets/7a269c68-22de-4e32-a0b6-c55fe32d8131" /> ### Relevant log output ```shell ``` ### OS mac os 26.1 ### GPU _No response_ Apple M1 Max _No response_ ### Ollama version 0.13
GiteaMirror added the bug label 2026-05-04 22:53:04 -05:00
GiteaMirror commented 2026-05-04 22:53:09 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 20, 2025):

deepseek-ocr does not perform well as a chatbot. It is very sensitive to variations in prompts, and it is recommended to use specific prompts for processing images.

<!-- gh-comment-id:3556854416 --> @rick-github commented on GitHub (Nov 20, 2025): deepseek-ocr does not perform well as a chatbot. It is very sensitive to variations in prompts, and it is recommended to use [specific prompts](https://github.com/deepseek-ai/DeepSeek-OCR/?tab=readme-ov-file#prompts-examples) for processing images.
GiteaMirror commented 2026-05-04 22:53:15 -05:00
Author
Owner
Copy Link

@amey6992 commented on GitHub (Nov 20, 2025):

** issue with deepseek-ocr **

  • did pull the model
  • When I run it, I get an error
  • Error: 500 Internal Server Error: unable to load model: /home/.ollama/models/blobs/sha256-3a18673ff291a1d8de94d490877127899356d33a18028d5f3945bf245c11b02c
  • OS - Ubuntu 22
  • free memory is about 160Gbs, the other model llama3.2 worked well
<!-- gh-comment-id:3559804775 --> @amey6992 commented on GitHub (Nov 20, 2025): ** issue with deepseek-ocr ** - did pull the model - When I run it, I get an error - `Error: 500 Internal Server Error: unable to load model: /home/.ollama/models/blobs/sha256-3a18673ff291a1d8de94d490877127899356d33a18028d5f3945bf245c11b02c` - OS - Ubuntu 22 - free memory is about 160Gbs, the other model **llama3.2** worked well
GiteaMirror commented 2026-05-04 22:53:18 -05:00
Author
Owner
Copy Link

@maternion commented on GitHub (Nov 21, 2025):

@amey6992 which ollama version are you on? To run deepseek-ocr you need v0.13.0. But if you are on that maybe open a new issue and post ollama logs.

<!-- gh-comment-id:3562913072 --> @maternion commented on GitHub (Nov 21, 2025): @amey6992 which ollama version are you on? To run deepseek-ocr you need v0.13.0. But if you are on that maybe open a new issue and post [ollama logs](https://docs.ollama.com/troubleshooting).
GiteaMirror commented 2026-05-04 22:53:19 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 21, 2025):

#13177

<!-- gh-comment-id:3562918586 --> @rick-github commented on GitHub (Nov 21, 2025): #13177
GiteaMirror commented 2026-05-04 22:53:21 -05:00
Author
Owner
Copy Link

@skyksl066 commented on GitHub (Nov 26, 2025):

** issue with deepseek-ocr **

  • did pull the model
  • When I run it, I get an error
  • Error: 500 Internal Server Error: unable to load model: /home/.ollama/models/blobs/sha256-3a18673ff291a1d8de94d490877127899356d33a18028d5f3945bf245c11b02c
  • OS - Ubuntu 22
  • free memory is about 160Gbs, the other model llama3.2 worked well

It looks like this issue is caused by an older Ollama version.
DeepSeek-OCR requires a newer runtime, and updating Ollama fixes the model-loading error.

Please update Ollama to v0.13.0 or later and try again:

👉 https://github.com/ollama/ollama/releases

After the upgrade, restart the service and the model should load normally.

<!-- gh-comment-id:3578177352 --> @skyksl066 commented on GitHub (Nov 26, 2025): > ** issue with deepseek-ocr ** > > * did pull the model > * When I run it, I get an error > * `Error: 500 Internal Server Error: unable to load model: /home/.ollama/models/blobs/sha256-3a18673ff291a1d8de94d490877127899356d33a18028d5f3945bf245c11b02c` > * OS - Ubuntu 22 > * free memory is about 160Gbs, the other model **llama3.2** worked well It looks like this issue is caused by an older Ollama version. DeepSeek-OCR requires a newer runtime, and updating Ollama fixes the model-loading error. Please update Ollama to v0.13.0 or later and try again: 👉 https://github.com/ollama/ollama/releases After the upgrade, restart the service and the model should load normally.
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#70765
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?