Downloads · 30 days
0
BAGEL-Canvas-SFT-rushhour-Merged-600
denizakkoc/BAGEL-Canvas-SFT-rushhour-Merged-600
BAGEL-Canvas-SFT-rushhour-Merged-600 is a image-text-to-text model from denizakkoc. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for bagel. The card lists the license as apache-2.0.
Supervised fine-tune of BAGEL-Canvas on the Rush Hour block-sliding puzzle, teaching interleaved visual chain-of-thought: the model reasons step by step and renders the intermediate board states while deciding which c…
Access
Public
Updated Jul 6, 2026
Parameters
14.6B
29.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors29.5 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- bagel
- License
- apache-2.0
- Access
- Public
- Created
- Jul 6, 2026
- Updated
- Jul 6, 2026
- SHA
- 6f5735de
Try a prompt
Model card
From the Hugging Face model README
BAGEL-Canvas SFT — Rush Hour (Merged, step 600)
Supervised fine-tune of BAGEL-Canvas on the Rush Hour block-sliding puzzle, teaching interleaved visual chain-of-thought: the model reasons step by step and renders the intermediate board states while deciding which car to slide and in which direction.
This checkpoint is the merged model (base + LoRA adapters folded in) at training step 600, ready to load directly — no adapter merge needed.
Contents
| File | Description |
|---|---|
model.safetensors | Full merged BAGEL weights (~29 GB) |
ae.safetensors | VAE for image tokens |
llm_config.json, vit_config.json, generation_config.json, preprocessor_config.json | Model / component configs |
tokenizer.json, tokenizer_config.json, vocab.json, merges.txt | Tokenizer |
Usage
Load with the BAGEL-Canvas / MathCanvas training-and-inference code. Used as the GRPO starting policy in the Rush Hour RL experiments.
Provenance
- Base: BAGEL-Canvas (unified LMM, MoT).
- Fine-tuned on oracle-grounded Rush Hour reasoning traces (levels 1–5).
- Task
- Image-Text-to-Text
- Library
- bagel
- License
- apache-2.0
- Created
- Jul 6, 2026
- Updated
- Jul 6, 2026