Skip to content

Fix VLM GRPO notebook for modern TRL (conversational prompts, reward functions, dependencies) #377

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ahmedshahrukhali wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Fix VLM GRPO notebook for modern TRL (conversational prompts, reward functions, dependencies) #377

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
64412aa
Fix VLM GRPO training with conversational prompts (fixes #363)
ahmedshahrukhali Sep 23, 2026
45d0e36
Upgrade torchao in installation cell for Colab compatibility
ahmedshahrukhali Sep 23, 2026
3be3286
Created using Colab
ahmedshahrukhali Sep 24, 2026
6dc001d
commented original code + working changes + notebook run successful o…
ahmedshahrukhali Sep 25, 2026
ba3069f
fix issue #363 incl import (for colab) and function definitions (for …
ahmedshahrukhali Sep 28, 2026
45225cc
fix 363 + clean auth
ahmedshahrukhali Sep 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15,659 changes: 14,379 additions & 1,280 deletions notebooks/en/fine_tuning_vlm_grpo_trl.ipynb
View file
Open in desktop

Large diffs are not rendered by default.