Fine-tune PaliGemma for Image Description with Custom Dataset
This notebook guides you through fine-tuning PaliGemma, a powerful vision-language model, for bird description using JAX.
We'll leverage an existing portion of a bird species dataset and enrich it with descriptions for each bird. The resulting 3,922 image-description pairs will fuel the fine-tuning process.
Available on Colab Notebook
Available on Kaggle Notebook
Unable to determine this model's library. Check the
docs
.