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 #6222] /save does not preserve existing parameters #50399

New Issue
Open
opened 2026-04-28 15:37:11 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 15:37:11 -05:00
Owner
Copy Link

Originally created by @sdmorrey on GitHub (Aug 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6222

Originally assigned to: @pdevine on GitHub.

What is the issue?

I am working on a modelfile and did the following...

ollama run --verbose llama3.1:8b
/set parameter num_ctx 131072
/set parameter num_predict -2

/save llama3.1:8b-128k
/bye

I then kill and restart ollama and run the new modelfile

ollama run --verbose llama3.1:8b-128k

Performing a /show modefile shows that my parameters were saved but then I realize I want mlock

/set parameter use_mlock true
/save llama3.1:8b-128k
/bye

Now if I kill ollama and restart it with
ollama run --verbose llama3.1:8b-128k

Doing a show modelfile shows that the only parameter is use_mlock.

The expected behavior is that it would preserve pre-existing parameters between saves. That does not appear to be occuring.

OS

macOS

GPU

Other

CPU

Intel

Ollama version

0.3.3

Originally created by @sdmorrey on GitHub (Aug 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6222 Originally assigned to: @pdevine on GitHub. ### What is the issue? I am working on a modelfile and did the following... ``` ollama run --verbose llama3.1:8b /set parameter num_ctx 131072 /set parameter num_predict -2 /save llama3.1:8b-128k /bye ``` I then kill and restart ollama and run the new modelfile ``` ollama run --verbose llama3.1:8b-128k ``` Performing a /show modefile shows that my parameters were saved but then I realize I want mlock ``` /set parameter use_mlock true /save llama3.1:8b-128k /bye ``` Now if I kill ollama and restart it with ollama run --verbose llama3.1:8b-128k Doing a show modelfile shows that the only parameter is use_mlock. The expected behavior is that it would preserve pre-existing parameters between saves. That does not appear to be occuring. ### OS macOS ### GPU Other ### CPU Intel ### Ollama version 0.3.3
GiteaMirror added the bug label 2026-04-28 15:37:11 -05:00
GiteaMirror commented 2026-04-28 15:37:16 -05:00
Author
Owner
Copy Link

@Maltz42 commented on GitHub (Aug 7, 2024):

It also doesn't preserve messages prior to the current session anymore. It appears that particular thing broke beginning in v0.3.2 - maybe the parameters issue is related?

<!-- gh-comment-id:2272606629 --> @Maltz42 commented on GitHub (Aug 7, 2024): It also doesn't preserve messages prior to the current session anymore. It appears that particular thing broke beginning in v0.3.2 - maybe the parameters issue is related?
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#50399
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?