InternVL多模态

多模态微调 最麻烦的其实是数据准备:大体如下

一个字段要包含一个对应的图片

{
    "id": "000000033471",
    "image": ["coco/train2017/000000033471.jpg"],
    "conversations": [
      {
        "from": "human",
        "value": "<image>\nWhat are the colors of the bus in the image?"
      },
      {
        "from": "gpt",
        "value": "The bus in the image is white and red."
      }
    ]
  }
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值