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 #5198] use_mmap: Error: invalid int value [false] #3266

New Issue
Closed
opened 2026-04-12 13:48:47 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-12 13:48:47 -05:00
Owner
Copy Link

Originally created by @ghost on GitHub (Jun 21, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5198

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

When adding the use_mmap parameter to a modelfile, it used to be like this: PARAMETER use_mmap false. Since 0.1.45, this does not work, it wants an integer value. So I put PARAMETER use_mmap 0. This allows me to create the modelfile.

However, when attempting to run the model, it comes back with this error: Error: option "use_mmap" must be of type boolean

Seems like a cast was forgotten somewhere maybe?

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.1.45

Originally created by @ghost on GitHub (Jun 21, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5198 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? When adding the `use_mmap` parameter to a modelfile, it used to be like this: `PARAMETER use_mmap false`. Since 0.1.45, this does not work, it wants an integer value. So I put `PARAMETER use_mmap 0`. This allows me to create the modelfile. However, when attempting to run the model, it comes back with this error: `Error: option "use_mmap" must be of type boolean` Seems like a cast was forgotten somewhere maybe? ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.1.45
GiteaMirror added the bug label 2026-04-12 13:48:47 -05:00
GiteaMirror commented 2026-04-12 13:48:49 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Jun 21, 2024):

By downgrading to 0.1.44, I was able to create the model, and run it using 0.1.45. So this behavior changed between 0.1.44 and 0.1.45.

<!-- gh-comment-id:2182170669 --> @ghost commented on GitHub (Jun 21, 2024): By downgrading to 0.1.44, I was able to create the model, and run it using 0.1.45. So this behavior changed between 0.1.44 and 0.1.45.
GiteaMirror commented 2026-04-12 13:48:50 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 21, 2024):

Sorry about that. I recently change this to be a tri-state variable (unset, true or false) and missed the parsing logic for the modelfile. We'll get this fixed in the next release.

<!-- gh-comment-id:2182963712 --> @dhiltgen commented on GitHub (Jun 21, 2024): Sorry about that. I recently change this to be a tri-state variable (unset, true or false) and missed the parsing logic for the modelfile. We'll get this fixed in the next release.
GiteaMirror commented 2026-04-12 13:48:50 -05:00
Author
Owner
Copy Link

@ProjectMoon commented on GitHub (Jun 23, 2024):

I am not sure this is actually fix. I also had to downgrade to 0.1.44 again to create a model with use_mmap false, even with 0.1.46. I could create the model on latest version, but it would not run, with a similar issue about missing the boolean.

<!-- gh-comment-id:2184410487 --> @ProjectMoon commented on GitHub (Jun 23, 2024): I am not sure this is actually fix. I also had to downgrade to 0.1.44 again to create a model with use_mmap false, even with 0.1.46. I could create the model on latest version, but it would not run, with a similar issue about missing the boolean.
GiteaMirror commented 2026-04-12 13:48:51 -05:00
Author
Owner
Copy Link

@ProjectMoon commented on GitHub (Jun 23, 2024):

For a bit more clarity on this: on the latest version, I can create the model with use_mmap false. But when I try to run it, it says that parameter use_mmap must be of type boolean.

<!-- gh-comment-id:2185117849 --> @ProjectMoon commented on GitHub (Jun 23, 2024): For a bit more clarity on this: on the latest version, I can create the model with `use_mmap false`. But when I try to run it, it says that parameter use_mmap must be of type boolean.
GiteaMirror commented 2026-04-12 13:48:51 -05:00
Author
Owner
Copy Link

@ProjectMoon commented on GitHub (Jun 26, 2024):

Should this be reopened since there is another PR required for it? I don't think I can reopen it myself.

<!-- gh-comment-id:2190902648 --> @ProjectMoon commented on GitHub (Jun 26, 2024): Should this be reopened since there is another PR required for it? I don't think I can reopen it myself.
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#3266
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?