---
license: apache-2.0
base_model: ThinkMorph/ThinkMorph-SSL-Base
base_model_relation: finetune
pipeline_tag: any-to-any
library_name: bagel
datasets:
- ThinkMorph/Pretext-270K
- ThinkMorph/Instruct-180K
---

# ThinkMorph-SSL-Instruct

<p>
  <a href="https://huggingface.co/datasets/ThinkMorph/Pretext-270K"><img src="https://img.shields.io/badge/Pretext--270K-Dataset-yellow?logo=huggingface&logoColor=yellow" alt="Pretext-270K Dataset"/></a>
  <a href="https://huggingface.co/datasets/ThinkMorph/Instruct-180K"><img src="https://img.shields.io/badge/Instruct--180K-Dataset-yellow?logo=huggingface&logoColor=yellow" alt="Instruct-180K Dataset"/></a>
  <a href="https://huggingface.co/ThinkMorph/ThinkMorph-SSL-Base"><img src="https://img.shields.io/badge/ThinkMorph--SSL--Base-Model-orange?logo=huggingface&logoColor=orange" alt="ThinkMorph-SSL-Base Model"/></a>
</p>

## About

ThinkMorph-SSL-Instruct reasons with interleaved text and images. On a visual question it thinks
in text, generates intermediate images when they help (a zoomed-in crop, a depth map, a
bird's-eye view, the view from another position), and then answers.

It is trained from [BAGEL-7B-MoT](https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT) in two stages:

| Stage | Data | Model |
| --- | --- | --- |
| 1. Self-supervised pretext reasoning | [Pretext-270K](https://huggingface.co/datasets/ThinkMorph/Pretext-270K) | [ThinkMorph-SSL-Base](https://huggingface.co/ThinkMorph/ThinkMorph-SSL-Base) |
| 2. Instruction tuning | [Instruct-180K](https://huggingface.co/datasets/ThinkMorph/Instruct-180K) | ThinkMorph-SSL-Instruct (this model) |

## 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>
```

## Benchmarks

Results will be added with the paper.

## Citation

The citation will be added with the paper.