# Multimodal fine-tuning

A visual-language generation model fine-tuned for image-text retrieval tasks, improved based on google/flan-t5-xl

A vision-language generation model fine-tuned based on google/flan-t5-xxl, specifically designed for image-text retrieval tasks

A vision-language model based on ViT and GPT2 architectures, specifically fine-tuned for Pokémon description generation tasks

A model fine-tuned based on bert-base-uncased for identifying hateful meme text content