Downloads · 30 days
0
maze2d_easy_cot_native256_lastbranch_thinkfix_step5000
novastar114/maze2d_easy_cot_native256_lastbranch_thinkfix_step5000
maze2d_easy_cot_native256_lastbranch_thinkfix_step5000 is a machine learning model from novastar114. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
BAGEL-7B-MoT SFT checkpoint (ema weights only).
Access
Public
Updated Jul 5, 2026
Repo size
58.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors58.4 GB · 100%
At a glance
- License
- other
- Access
- Public
- Created
- Jul 5, 2026
- Updated
- Jul 5, 2026
- SHA
- 6eb6ea71
Model card
From the Hugging Face model README
maze2d_easy_cot_native256_lastbranch_thinkfix_step5000
BAGEL-7B-MoT SFT checkpoint (ema weights only).
- task: maze2d_easy variant: cot_thinkfix step: 5000
- native256 all-step CoT; canonical post-0608 thinkfix for lastbranch_v3 (<think> block fixed)
- file:
ema.safetensors(EMA weights; optimizer state NOT included — inference/eval/RL, not resume)
Load
This is an SFT delta on the BAGEL-7B-MoT base. Load with the base config/tokenizer/VAE/ViT from
BAGEL-7B-MoT and these EMA weights, e.g. the repo's eval runners:
--bagel-path <this repo> --bagel-base-path <BAGEL-7B-MoT>.
Image transforms: maze2d VAE 256/256 ViT 224/224 (q95); sokoban v8 VAE 512/256 ViT 336/224 (q95); pusht VAE 256/256 ViT 224/224 (q90, 96px render). Prompt is stop-required; CoT is all-step interleaved.
- License
- other
- Created
- Jul 5, 2026
- Updated
- Jul 5, 2026