Repository: LLaVA-CoT GitHub Repository
Paper: LLaVA-CoT on arXiv
Dataset Structure
Turkish - tr dataset
unzip image.zip
The train.jsonl file contains the question-answering data and is structured in the following format:
{
"id": "example_id",
"image": "example_image_path",
"conversations": [
{"from": "human", "value": "Lütfen resimdeki kırmızı metal nesnelerin sayısını belirtin."},
{"from": "gpt", "value":… See the full description on the dataset page: https://huggingface.co/datasets/berhaan/clevr-tr.
