Dataset card organized by task

README.md

@@ -18,36 +18,19 @@ datasets:
 ## About
 
 ThinkMorph-SSL-Base is [BAGEL-7B-MoT](https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT) after self-supervised pretext
-reasoning on [Pretext-270K](https://huggingface.co/datasets/ThinkMorph/Pretext-270K). In each training trace the model
-sees a corrupted image (grayscale, noisy, low-resolution, masked, warped, rotated or flipped, or
-cut into shuffled tiles), describes it, generates the restored image, and describes the result.
+reasoning on [Pretext-270K](https://huggingface.co/datasets/ThinkMorph/Pretext-270K). Given a corrupted image, it
+describes the image, generates the restored version, and describes the result. It was trained
+without questions and gives no answers.
 
-This repository holds the EMA weights at step 5,500, the starting point of
-[ThinkMorph-SSL-Instruct](https://huggingface.co/ThinkMorph/ThinkMorph-SSL-Instruct). The model has seen no
-questions or answers; for visual question answering, use ThinkMorph-SSL-Instruct.
+These are the EMA weights at step 5,500, the starting point of
+[ThinkMorph-SSL-Instruct](https://huggingface.co/ThinkMorph/ThinkMorph-SSL-Instruct).
 
 ## Usage
 
 The checkpoint has the same layout as BAGEL-7B-MoT and loads with the
-[BAGEL code](https://github.com/ByteDance-Seed/Bagel). Keep the VAE and tokenizer files shipped
-here. Prompt the model with the system prompt it was trained with:
-
-```text
-Use <think>...</think> for intermediate reasoning or planning.
-
-To generate an image, write <gen_image> followed by an image-size declaration:
-  <gen_image>[Image size: (height, width)]
-Generated images become part of your context and can inform subsequent reasoning. You may generate more than one image if needed.
-
-If the task requires a final textual answer, wrap it in <answer>...</answer>.
-If no textual answer is needed, the response may end after reasoning or image generation.
-
-Example:
-  <think>reasoning step</think>
-  <gen_image>[Image size: (512, 512)]
-  <think>observe and reason about the generated image</think>
-  <answer>final answer</answer>
-```
+[BAGEL code](https://github.com/ByteDance-Seed/Bagel). Its output is `<think>...</think>`, a
+generated image, then `<think>...</think>`. It was trained with the same system prompt as
+ThinkMorph-SSL-Instruct.
 
 ## Citation