Any-to-Any
bagel
custom_code
ThinkMorph-SSL-Base / README.md
kuvvi's picture
Dataset card organized by task
2469524 verified
|
Raw History Blame Contribute Delete
1.48 kB
metadata
license: apache-2.0
base_model: ByteDance-Seed/BAGEL-7B-MoT
base_model_relation: finetune
pipeline_tag: any-to-any
library_name: bagel
datasets:
  - ThinkMorph/Pretext-270K

ThinkMorph-SSL-Base

Pretext-270K Dataset ThinkMorph-SSL-Instruct Model

About

ThinkMorph-SSL-Base is BAGEL-7B-MoT after self-supervised pretext reasoning on 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. It is the starting point of ThinkMorph-SSL-Instruct.

Usage

The checkpoint has the same layout as BAGEL-7B-MoT and loads with the BAGEL code. Its output is <think>...</think>, a generated image, then <think>...</think>. It was trained with the same system prompt as ThinkMorph-SSL-Instruct.

Citation

The citation will be added with the paper.