AdaptLLM/food-visual-instructions download history
AdaptLLM/food-visual-instructions is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,203 times (40 in the last 7 days), and 5,865 times in total. It ranks #16,820 among datasets by monthly downloads.
Adapting Multimodal Large Language Models to Domains via Post-Training (EMNLP 2025) This repos contains the food visual instructions for post-training MLLMs in our paper: On Domain-Specific Post-Training for Multimodal Large Language Models. The main project page is: Adapt-MLLM-to-Domains
Models trained on food-visual-instructions
1 models list it as training data.
- AdaptLLM/food-Qwen2.5-VL-3B-Instruct 20 downloads in 30 days