From cd7156fb34ddf9a8c04fcd640a4067933461d44e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?= <45557362+qgallouedec@users.noreply.github.com> Date: Fri, 13 Dec 2024 20:29:35 +0100 Subject: [PATCH] =?UTF-8?q?=20=F0=9F=91=80=20Add=20"PaliGemma=20?= =?UTF-8?q?=F0=9F=A4=9D=20Direct=20Preference=20Optimization"=20in=20commu?= =?UTF-8?q?nity=20tutorials=20(#2475)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- docs/source/community_tutorials.md | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/docs/source/community_tutorials.md b/docs/source/community_tutorials.md index 6aaf03f1b3..4192012045 100644 --- a/docs/source/community_tutorials.md +++ b/docs/source/community_tutorials.md @@ -15,10 +15,11 @@ Community tutorials are made by active members of the Hugging Face community tha # Vision Language Models -| Task | Class | Description | Author | Tutorial | Colab | -| --------------- | -------------- | ---------------------------------------------------------------------------- | ------------------------------------------------------ | -------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| Visual QA | [`SFTTrainer`] | Fine-tuning Qwen2-VL-7B for visual question answering on ChartQA dataset | [Sergio Paniego](https://huggingface.co/sergiopaniego) | [Link](https://huggingface.co/learn/cookbook/fine_tuning_vlm_trl) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/cookbook/blob/main/notebooks/en/fine_tuning_vlm_trl.ipynb) | -| SEO Description | [`SFTTrainer`] | Fine-tuning Qwen2-VL-7B for generating SEO-friendly descriptions from images | [Philipp Schmid](https://huggingface.co/philschmid) | [Link](https://www.philschmid.de/fine-tune-multimodal-llms-with-trl) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/philschmid/deep-learning-pytorch-huggingface/blob/main/training/fine-tune-multimodal-llms-with-trl.ipynb) | +| Task | Class | Description | Author | Tutorial | Colab | +| --------------- | -------------- | ---------------------------------------------------------------------------- | ------------------------------------------------------ | -------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Visual QA | [`SFTTrainer`] | Fine-tuning Qwen2-VL-7B for visual question answering on ChartQA dataset | [Sergio Paniego](https://huggingface.co/sergiopaniego) | [Link](https://huggingface.co/learn/cookbook/fine_tuning_vlm_trl) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/cookbook/blob/main/notebooks/en/fine_tuning_vlm_trl.ipynb) | +| SEO Description | [`SFTTrainer`] | Fine-tuning Qwen2-VL-7B for generating SEO-friendly descriptions from images | [Philipp Schmid](https://huggingface.co/philschmid) | [Link](https://www.philschmid.de/fine-tune-multimodal-llms-with-trl) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/philschmid/deep-learning-pytorch-huggingface/blob/main/training/fine-tune-multimodal-llms-with-trl.ipynb) | +| Visual QA | [`DPOTrainer`] | PaliGemma 🤝 Direct Preference Optimization | [Merve Noyan](https://huggingface.co/merve) | [Link](https://github.com/merveenoyan/smol-vision/blob/main/PaliGemma_DPO.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/merveenoyan/smol-vision/blob/main/PaliGemma_DPO.ipynb) | ## Contributing