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 #2009] Import pytorch adapter .bin files #47673

New Issue
Closed
opened 2026-04-28 04:52:45 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 04:52:45 -05:00
Owner
Copy Link

Originally created by @PhilipAmadasun on GitHub (Jan 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2009

Originally assigned to: @pdevine on GitHub.

Has anyone on here successfully created a fine-tuned mistral model with:

curl http://server.local:11434/api/create -d '{
  "name": "test_mistral",
  "modelfile": "FROM mistral\nADAPTER /home/robot/adapter_model.bin"
}'

Apparently .bin files aren't in pytorch format so it doesn't work does anyone actually use this method or just straight up export a gguf?

Originally created by @PhilipAmadasun on GitHub (Jan 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2009 Originally assigned to: @pdevine on GitHub. Has anyone on here successfully created a fine-tuned mistral model with: ``` curl http://server.local:11434/api/create -d '{ "name": "test_mistral", "modelfile": "FROM mistral\nADAPTER /home/robot/adapter_model.bin" }' ``` Apparently .bin files aren't in pytorch format so it doesn't work does anyone actually use this method or just straight up export a gguf?
GiteaMirror added the feature request label 2026-04-28 04:52:45 -05:00
GiteaMirror commented 2026-04-28 04:52:48 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Jan 16, 2024):

One thing you need to do is create the model properly. FROM should be the sha256 digest of the blob you uploaded with the adapter weights. Check the API docs.

<!-- gh-comment-id:1893121833 --> @easp commented on GitHub (Jan 16, 2024): One thing you need to do is create the model properly. FROM should be the sha256 digest of the blob you uploaded with the adapter weights. Check the API docs.
GiteaMirror commented 2026-04-28 04:52:48 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 10, 2024):

I know this is an older issue, but let's track this in #4618. I do have adapters working w/ NPZ files created w/ MLX (#5524).

EDIT: On second thought, let's track it in #156

<!-- gh-comment-id:2221180587 --> @pdevine commented on GitHub (Jul 10, 2024): I know this is an older issue, but let's track this in #4618. I do have adapters working w/ NPZ files created w/ MLX (#5524). EDIT: On second thought, let's track it in #156
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 feature request
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#47673
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?