-
Notifications
You must be signed in to change notification settings - Fork 2.1k
💎 Gemma 3 VLM SFT example script for single-image and multi-image #3131
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.
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
Conversation
very nice! |
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
examples/scripts/sft_vlm_gemma3.py
Outdated
with zipfile.ZipFile(zip_path, "r") as zip_ref: | ||
zip_ref.extractall(extract_folder) | ||
|
||
dataset = DatasetDict({"test": [format_data(sample) for sample in dataset[dataset_train_split]]}) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
possible to use
dataset = dataset.map(format_data)
instead?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Updated!
Gemma 3
VLM SFT example script for single-image and multi-imageThere was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks!
…ggingface#3131) Co-authored-by: Quentin Gallouédec <[email protected]> Co-authored-by: Quentin Gallouédec <[email protected]>
…ggingface#3131) Co-authored-by: Quentin Gallouédec <[email protected]> Co-authored-by: Quentin Gallouédec <[email protected]> log answer key to wandb all Table HTML logging table bump patch hmm formatting html esacape reward isnt string [Liger] Liger KTO support (huggingface#2812) Co-authored-by: Kashif Rasul <[email protected]> Co-authored-by: Quentin Gallouédec <[email protected]> 🏃 Migrate CI to self-hosted runners (huggingface#3174) ❤️🩹 [CI] fix transformers dev CI failure (huggingface#3176) Co-authored-by: Quentin Gallouédec <[email protected]> ⏯️ Fix: handle None inputs when resuming GRPO Trainer from checkpoint (huggingface#3148) Co-authored-by: Quentin Gallouédec <[email protected]> 📎 Fix is_clipped to compute the effective clip_ratio (huggingface#3175) Co-authored-by: Quentin Gallouédec <[email protected]> Co-authored-by: Quentin Gallouédec <[email protected]> Fix breaking typo for flash_attention reducing_memory_usage.md (huggingface#3190) Show unique prompts in GRPO WandB tables (huggingface#3191) 🐗 [CI] Fix trufflehog false positives (huggingface#3192) [GRPO] Improve completion length logging (huggingface#3188) preliminary openai compatible endpoint early concept, needs refining dedupe debug print some slop to work on unslop, missing hist almost valid pseudocode middle-ware monkey patch in mp.Pool()... remove unused More accurate .md need gpu renting lambda again much nicer small aider-chat and datasets conflict risky reqs change should work, but hacky some insights, but monkeypatching probably wont suffice refactor: Rewrite test script to use SWE-bench dataset with MultiProcessAider refactor: Remove logging statements from test.py one step closer finally, the correct abstraction doc todo unslop unslop undo accidental black cleaner abstraction new abstraction
…ggingface#3131) Co-authored-by: Quentin Gallouédec <[email protected]> Co-authored-by: Quentin Gallouédec <[email protected]>
What does this PR do?
This PR presents a standalone SFT example script for VLM 💎
Gemma 3
.It includes examples for both single-image and multi-image inputs.
@merveenoyan @qgallouedec @burtenshaw
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.