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 #2488] How can fine tune with ollama? #1450

New Issue
Closed
opened 2026-04-12 11:20:59 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 11:20:59 -05:00
Owner
Copy Link

Originally created by @KDH-Korea on GitHub (Feb 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2488

I want to fine-tune the Mistral model imported using Ollama, but there is no information available, and it's even more challenging to find information in Korea where not many people are familiar with Ollama. I would appreciate it if you could provide information on how to fine-tune the model using Ollama.

Originally created by @KDH-Korea on GitHub (Feb 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2488 I want to fine-tune the Mistral model imported using Ollama, but there is no information available, and it's even more challenging to find information in Korea where not many people are familiar with Ollama. I would appreciate it if you could provide information on how to fine-tune the model using Ollama.
GiteaMirror commented 2026-04-12 11:21:00 -05:00
Author
Owner
Copy Link

@Zig1375 commented on GitHub (Feb 14, 2024):

+1

<!-- gh-comment-id:1943426642 --> @Zig1375 commented on GitHub (Feb 14, 2024): +1
GiteaMirror commented 2026-04-12 11:21:00 -05:00
Author
Owner
Copy Link

@chuangtc commented on GitHub (Feb 19, 2024):

First fine-tune open-source hugging face AI model.

https://huggingface.co/docs/transformers/training

Then do quantization and convert the model to GGUF format and re-upload to hugging face.

https://mlabonne.github.io/blog/posts/Quantize_Llama_2_models_using_ggml.html

Then run it with Modelfile with the GGUF format model.

https://www.markhneedham.com/blog/2023/10/18/ollama-hugging-face-gguf-models/

<!-- gh-comment-id:1951777503 --> @chuangtc commented on GitHub (Feb 19, 2024): ### First fine-tune open-source hugging face AI model. https://huggingface.co/docs/transformers/training ### Then do quantization and convert the model to GGUF format and re-upload to hugging face. https://mlabonne.github.io/blog/posts/Quantize_Llama_2_models_using_ggml.html ### Then run it with Modelfile with the GGUF format model. https://www.markhneedham.com/blog/2023/10/18/ollama-hugging-face-gguf-models/
GiteaMirror commented 2026-04-12 11:21:01 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Feb 20, 2024):

Thanks for the guides @chuangtc! I'm going to merge this with https://github.com/ollama/ollama/issues/156 just to keep the issues tidy.

<!-- gh-comment-id:1955251654 --> @jmorganca commented on GitHub (Feb 20, 2024): Thanks for the guides @chuangtc! I'm going to merge this with https://github.com/ollama/ollama/issues/156 just to keep the issues tidy.
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
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#1450
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?