github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #5788] Support LoRA GGUF Adapters #3606

New Issue
Closed
opened 2026-04-12 14:21:20 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 14:21:20 -05:00
Owner
Copy Link

Originally created by @suncloudsmoon on GitHub (Jul 19, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5788

Recently, llama.cpp added support for LoRA GGUF adapters, replacing the old GGML format. I would love to see this feature extended to Ollama if it's possible. Currently, Ollama only supports GGML adapters as shown in modelfile.md.

The ADAPTER instruction is an optional instruction that specifies any LoRA adapter that should apply to the base model. The value of this instruction should be an absolute path or a path relative to the Modelfile and the file must be in a GGML file format. The adapter should be tuned from the base model otherwise the behaviour is undefined.

Originally created by @suncloudsmoon on GitHub (Jul 19, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5788 Recently, [llama.cpp added support for LoRA GGUF adapters](https://github.com/ggerganov/llama.cpp/pull/8332), replacing the old GGML format. I would love to see this feature extended to Ollama if it's possible. Currently, Ollama only supports GGML adapters as shown in [```modelfile.md```](https://github.com/ollama/ollama/blob/main/docs/modelfile.md#adapter). > The ADAPTER instruction is an optional instruction that specifies any LoRA adapter that should apply to the base model. The value of this instruction should be an absolute path or a path relative to the Modelfile and the file must be in a GGML file format. The adapter should be tuned from the base model otherwise the behaviour is undefined.
GiteaMirror added the feature request label 2026-04-12 14:21:20 -05:00
GiteaMirror commented 2026-04-12 14:21:21 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 12, 2024):

It actually is supported! We've removed support for GGLA, but the ADAPTER command will work with both GGUF and Safetensors files. Check out the import docs

<!-- gh-comment-id:2347342520 --> @pdevine commented on GitHub (Sep 12, 2024): It actually is supported! We've removed support for GGLA, but the `ADAPTER` command will work with both GGUF and Safetensors files. Check out the [import docs](https://github.com/ollama/ollama/blob/main/docs/import.md#Importing-a-fine-tuned-adapter-from-Safetensors-weights)
GiteaMirror commented 2026-04-12 14:21:21 -05:00
Author
Owner
Copy Link

@rbrisita commented on GitHub (Sep 19, 2024):

Would be great if it was also a REPL command to dynamically load adapters so that the Modelfile and create command weren't needed.

<!-- gh-comment-id:2362212699 --> @rbrisita commented on GitHub (Sep 19, 2024): Would be great if it was also a REPL command to dynamically load adapters so that the Modelfile and `create` command weren't needed.
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#3606
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?