[GH-ISSUE #1] Fine-tuning #3

Open
opened 2026-10-26 21:09:46 +00:00 by bsakaguchi · 1 comment
Owner

Originally created by @Pengjie-W on GitHub (Dec 13, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/1

Great job! Do you have any code for fine-tuning?

Originally created by @Pengjie-W on GitHub (Dec 13, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/1 Great job! Do you have any code for fine-tuning?
Author
Owner

@hinsonan commented on GitHub (Dec 19, 2024):

i think you can finetune this model using hugging face SFT or Trainer. It should follow that format since its a hugging face format

<!-- gh-comment-id:2555453832 --> @hinsonan commented on GitHub (Dec 19, 2024): i think you can finetune this model using hugging face SFT or Trainer. It should follow that format since its a hugging face format
Sign in to join this conversation.
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepSeek-VL2#3
No description provided.