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 #11028] Is it possible to use custom models fine-tuned on my local dataset with Ollama? #69333

New Issue
Closed
opened 2026-05-04 17:49:09 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 17:49:09 -05:00
Owner
Copy Link

Originally created by @barancaki on GitHub (Jun 9, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11028

Hi!

First of all, thanks for the awesome project. I’ve been experimenting with Ollama and really enjoy how easy it is to run models locally.

I was wondering:
• Is it currently possible to use a custom LLM that I’ve fine-tuned on my own dataset (e.g., using LoRA or QLoRA)?
• If yes, what would be the recommended process to package and load it into Ollama?
• If no, are there any plans to support this in future releases?

Thanks in advance for your help!

Originally created by @barancaki on GitHub (Jun 9, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11028 Hi! First of all, thanks for the awesome project. I’ve been experimenting with Ollama and really enjoy how easy it is to run models locally. I was wondering: • Is it currently possible to use a custom LLM that I’ve fine-tuned on my own dataset (e.g., using LoRA or QLoRA)? • If yes, what would be the recommended process to package and load it into Ollama? • If no, are there any plans to support this in future releases? Thanks in advance for your help!
GiteaMirror added the feature request label 2026-05-04 17:49:09 -05:00
GiteaMirror commented 2026-05-04 17:49:10 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 9, 2025):

Is it currently possible to use a custom LLM that I’ve fine-tuned on my own dataset (e.g., using LoRA or QLoRA)?

Yes, if the base model is supported by ollama.

what would be the recommended process to package and load it into Ollama?

Depends on what the fine-tuning process produces. If it's a LoRA adapter, create a Modelfile as described here. Some fune-tuners support creating a Safetensors file, which can be imported as described here. unlsoth goes as far as creating a GGUF and Modelfile which you can just pull from HF with ollama pull.

<!-- gh-comment-id:2956657201 --> @rick-github commented on GitHub (Jun 9, 2025): > Is it currently possible to use a custom LLM that I’ve fine-tuned on my own dataset (e.g., using LoRA or QLoRA)? Yes, if the base model is supported by ollama. > what would be the recommended process to package and load it into Ollama? Depends on what the fine-tuning process produces. If it's a LoRA adapter, create a Modelfile as described [here](https://github.com/ollama/ollama/blob/main/docs/import.md#Importing-a-fine-tuned-adapter-from-Safetensors-weights). Some fune-tuners support creating a Safetensors file, which can be imported as described [here](https://github.com/ollama/ollama/blob/main/docs/import.md#Importing-a-model-from-Safetensors-weights). unlsoth goes as far as creating a [GGUF and Modelfile](https://docs.unsloth.ai/basics/tutorial-how-to-finetune-llama-3-and-use-in-ollama) which you can just pull from HF with `ollama pull`.
GiteaMirror commented 2026-05-04 17:49:11 -05:00
Author
Owner
Copy Link

@barancaki commented on GitHub (Jun 11, 2025):

Thank you so much @rick-github

<!-- gh-comment-id:2962091397 --> @barancaki commented on GitHub (Jun 11, 2025): Thank you so much @rick-github
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#69333
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?