Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Conversation

@oelachqar
Copy link
Contributor

Description

Related issues

Fixes # (issue)

Before submitting

  • This PR only changes documentation. (You can ignore the following checks in that case)
  • Did you read the contributor guideline Pull Request guidelines?
  • Did you link the issue(s) related to this PR in the section above?
  • Did you add / update tests where needed?

Reviewers

At least one review from a member of oumi-ai/oumi-staff is required.

@oelachqar oelachqar requested a review from wizeng23 October 19, 2025 00:25
@oelachqar oelachqar marked this pull request as ready for review October 19, 2025 00:29
@oelachqar oelachqar changed the title [WIP] Add Qwen3 VL 4B config Add Qwen3 VL 4B config Oct 19, 2025
@oelachqar oelachqar removed the request for review from wizeng23 October 20, 2025 15:33
@oelachqar oelachqar added this pull request to the merge queue Oct 20, 2025
Merged via the queue into main with commit 6eb9b03 Oct 20, 2025
4 checks passed
@oelachqar oelachqar deleted the wizeng/qwen3vl branch October 20, 2025 15:33
@@ -0,0 +1,82 @@
# LoRA fine-tune config for Qwen3 VL 4B Instruct.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Change to FFT?

# - Log into WandB (`wandb login`) or disable `enable_wandb`
#
# Usage:
# oumi train -c configs/recipes/vision/qwen3_vl/sft/4b_instruct_lora_train.yaml
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ditto

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants