LLaVA Instruct
Visual instruction tuning dataset. Contains 158k unique language-image instruction-following samples to make LLMs 'see'.
加载
from datasets import load_dataset
ds = load_dataset("liuhaotian/LLaVA-Instruct-150K")预览示例数据
{
"image": "coco_train_000000581929.jpg",
"conversations": [
{ "from": "human", "value": "What is unusual about this image?" },
{ "from": "gpt", "value": "The man is ironing clothes on the back of a taxi..." }
]
}常见问题
LLaVA Instruct 可以商用吗?
不能用于产品——LLaVA Instruct 采用 CC-BY-NC 4.0,仅限研究等非商业用途。商业微调请改用同类别中宽松许可的数据集。
LLaVA Instruct 有多少数据?需要全部使用吗?
LLaVA Instruct 包含 158k Samples。通常不需要全部:风格和格式微调只需几百到几千条样本——先加载切片(如 split="train[:1000]"),质量到达瓶颈时再扩大规模。
LLaVA Instruct 最适合做什么?
Adding image understanding to an open LLM (the LLaVA recipe)。它属于数据集中心的「视觉」板块,那里有替代和互补的数据集。