[GH-ISSUE #8595] Train Ollama models using custom data #5558

Closed
opened 2026-04-12 16:49:00 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @samrudha01codespace on GitHub (Jan 26, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8595

Can users train the small ollama models using there datasets?

Originally created by @samrudha01codespace on GitHub (Jan 26, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8595 Can users train the small ollama models using there datasets?
GiteaMirror added the model label 2026-04-12 16:49:00 -05:00
Author
Owner

@rick-github commented on GitHub (Jan 26, 2025):

MacOS: https://www.youtube.com/watch?v=3UQ7GY9hNwk
Windows, Linux: https://www.youtube.com/watch?v=dMY3dBLojTk

<!-- gh-comment-id:2614499357 --> @rick-github commented on GitHub (Jan 26, 2025): MacOS: https://www.youtube.com/watch?v=3UQ7GY9hNwk Windows, Linux: https://www.youtube.com/watch?v=dMY3dBLojTk
Author
Owner

@Meshwa428 commented on GitHub (Jan 27, 2025):

Can users train the small ollama models using there datasets?

you mean finetune gguf models?? then not possible at current moment, and wont ever be. Because gguf is just a file format to efficiently quantize and save models.

<!-- gh-comment-id:2616486877 --> @Meshwa428 commented on GitHub (Jan 27, 2025): > Can users train the small ollama models using there datasets? you mean finetune gguf models?? then not possible at current moment, and wont ever be. Because gguf is just a file format to efficiently quantize and save models.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#5558