BeichenZhang/ETCHR-SFT-400K

ETCHR SFT-400K 是用于将被动指令遵循图像编辑器（基于 FLUX.2-klein-base-9B 构建）转换为自主的、问题条件的视觉推理助手的SFT训练数据。它包含400,000个样本，涵盖五个任务（细粒度感知、图表理解、迷宫求解、拼图游戏和空间理解）。每个样本包含原始图像、针对该图像的理解问题（作为编辑提示）以及真实编辑，这有助于理解模型回答该问题。ETCHR SFT-400K is the SFT training data for transfering a passive instruction-following image editor (built on FLUX.2-klein-base-9B) into an autonomous, question-conditioned visual reasoning assistant. It contains 400,000 samples of five tasks (Fine-grained Perception, Chart Understanding, Maze Solving, Jigsaw Puzzle and Spatial Understanding). Each sample contains the raw image, an understanding question for this image as the editing prompt, and the groundtruth edit which helps the understanding model to answer this question.