Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
merve 
posted an update 6 days ago
Post
2465
Fine-tune Gemma3n on videos with audios inside with Colab A100 🔥
Just dropped the notebook where you can learn how to fine-tune Gemma3n on images+audio+text at the same time!

keep in mind, it's made for educational purposes 🫡 we do LoRA, audio resampling & video downsampling to be able to train <40GB VRAM

stretch modalities and unfreeze layers as you wish! 🙏🏻 merve/smol-vision

Hey! Is there a chance we could have a chat? I have a specific vision-text dataset I wNt to train Gemma 3n on without losing audio but I’m a little stuck

In this post