maze2d_easy_cot_native256_lastbranch_step5000

BAGEL-7B-MoT SFT checkpoint (ema weights only).

• task: maze2d_easy variant: cot step: 5000
• native256 all-step CoT; key step = LAST decisive branch (lastbranch_v3)
• 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.