Dataset Viewer
Auto-converted to Parquet Duplicate
Search is not available for this dataset
image
imagewidth (px)
975
1.15k

logo

visitors GitHub Repo stars GitHub Code License GitHub last commit GitHub pull request Collection

GitHub Trend

Ⅰ 数据集

原始来源:

其中部分为中文数据,部分为英文数据。问答内容经过翻译,对中文支持更友好,进一步经过整理并resize(pretrain分辨率128×128,sft分辨率160×160)。

(pretrain_i2t.parquet) 预训练数据集格式:

列名: conversations (json string), image_bytes (binary), image_names (string)

conversations 示例:
[
  {"role": "user", "content": "提供给定图像的简要描述。\n<image>"},
  {"role": "assistant", "content": "橄榄油是自由使用的健康成分。"}
]
image_bytes: <图像二进制数据>

(sft_i2t.parquet) 单图指令微调数据集格式:

列名: conversations (json string), image_bytes (binary), image_names (string)

conversations 示例:
[
  {"role": "user", "content": "闹钟的位置对睡眠质量有什么影响?<image>"},
  {"role": "assistant", "content": "把数字闹钟放在床头柜..."}
]
image_bytes: <图像二进制数据>

注:sft_i2t.parquet 共约 58 万条数据,其中约 23.6 万条为含图对话(i2t),约 34.6 万条为纯文本对话(t2t),后者用于保持模型的基础语言能力。

数据集下载地址:(ModelScope | HuggingFace)

Downloads last month
2,293

Models trained or fine-tuned on jingyaogong/minimind-v_dataset

Collection including jingyaogong/minimind-v_dataset