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 #4523] GGUF imported model crashes only in v0.1.38 #28596

New Issue
Closed
opened 2026-04-22 07:00:16 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-22 07:00:16 -05:00
Owner
Copy Link

Originally created by @mindspawn on GitHub (May 19, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4523

What is the issue?

heegyu/EEVE-Korean-Instruct-10.8B-v1.0-GGUF worked in all prior versions of ollama. Since v0.1.38 it core dumps.
I have temporarily reverted to v0.1.37 to resolve the issue. Any help is appreciated.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.38

Originally created by @mindspawn on GitHub (May 19, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4523 ### What is the issue? heegyu/EEVE-Korean-Instruct-10.8B-v1.0-GGUF worked in all prior versions of ollama. Since v0.1.38 it core dumps. I have temporarily reverted to v0.1.37 to resolve the issue. Any help is appreciated. ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.38
GiteaMirror added the createbug labels 2026-04-22 07:00:16 -05:00
GiteaMirror commented 2026-04-22 07:00:18 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (May 20, 2024):

@mindspawn Can you attach the logs and the Modelfile? Also, do you have a link to the gguf binary, or did you convert it yourself?

<!-- gh-comment-id:2120984752 --> @pdevine commented on GitHub (May 20, 2024): @mindspawn Can you attach the logs and the Modelfile? Also, do you have a link to the gguf binary, or did you convert it yourself?
GiteaMirror commented 2026-04-22 07:00:18 -05:00
Author
Owner
Copy Link

@mindspawn commented on GitHub (May 21, 2024):

@mindspawn Can you attach the logs and the Modelfile? Also, do you have a link to the gguf binary, or did you convert it yourself?

I used the f16 version from here: https://huggingface.co/heegyu/EEVE-Korean-Instruct-10.8B-v1.0-GGUF/tree/main

For Modelfile, all I have in it is FROM ./ggml-model-f16.gguf

Unfortunately, it is deployed in an environment where I am unable to pull log files from. I have been using at least the last 4-5 versions of ollama with no issues. Great application by the way :)

<!-- gh-comment-id:2121738774 --> @mindspawn commented on GitHub (May 21, 2024): > @mindspawn Can you attach the logs and the Modelfile? Also, do you have a link to the gguf binary, or did you convert it yourself? I used the f16 version from here: https://huggingface.co/heegyu/EEVE-Korean-Instruct-10.8B-v1.0-GGUF/tree/main For Modelfile, all I have in it is FROM ./ggml-model-f16.gguf Unfortunately, it is deployed in an environment where I am unable to pull log files from. I have been using at least the last 4-5 versions of ollama with no issues. Great application by the way :)
GiteaMirror commented 2026-04-22 07:00:19 -05:00
Author
Owner
Copy Link

@joshyan1 commented on GitHub (Jun 25, 2024):

Hey @mindspawn, does this issue still seem to happen for you? I can't seem to reproduce it on the latest version on Mac. If it is happening, could you clarify what steps you take before the issue occurs?

<!-- gh-comment-id:2190114590 --> @joshyan1 commented on GitHub (Jun 25, 2024): Hey @mindspawn, does this issue still seem to happen for you? I can't seem to reproduce it on the latest version on Mac. If it is happening, could you clarify what steps you take before the issue occurs?
GiteaMirror commented 2026-04-22 07:00:21 -05:00
Author
Owner
Copy Link

@mindspawn commented on GitHub (Jun 28, 2024):

Hey @mindspawn, does this issue still seem to happen for you? I can't seem to reproduce it on the latest version on Mac. If it is happening, could you clarify what steps you take before the issue occurs?

Hi @joshyan1 thanks for following up. Unfortunately I've transitioned to vllm since and itay be a while before I cam verify this again. Perhaps we cancel the issue for now?

<!-- gh-comment-id:2197118472 --> @mindspawn commented on GitHub (Jun 28, 2024): > Hey @mindspawn, does this issue still seem to happen for you? I can't seem to reproduce it on the latest version on Mac. If it is happening, could you clarify what steps you take before the issue occurs? Hi @joshyan1 thanks for following up. Unfortunately I've transitioned to vllm since and itay be a while before I cam verify this again. Perhaps we cancel the issue for now?
GiteaMirror commented 2026-04-22 07:00:21 -05:00
Author
Owner
Copy Link

@joshyan1 commented on GitHub (Jun 30, 2024):

Hey @mindspawn, does this issue still seem to happen for you? I can't seem to reproduce it on the latest version on Mac. If it is happening, could you clarify what steps you take before the issue occurs?

Hi @joshyan1 thanks for following up. Unfortunately I've transitioned to vllm since and itay be a while before I cam verify this again. Perhaps we cancel the issue for now?

Hey @mindspawn, okay thanks. Feel free to open up this issue again if you experience it.

<!-- gh-comment-id:2198799880 --> @joshyan1 commented on GitHub (Jun 30, 2024): > > Hey @mindspawn, does this issue still seem to happen for you? I can't seem to reproduce it on the latest version on Mac. If it is happening, could you clarify what steps you take before the issue occurs? > > Hi @joshyan1 thanks for following up. Unfortunately I've transitioned to vllm since and itay be a while before I cam verify this again. Perhaps we cancel the issue for now? Hey @mindspawn, okay thanks. Feel free to open up this issue again if you experience it.
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 create
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#28596
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?