cof-readiness-v3

Aelien/cof-readiness-v3

cof-readiness-v3 is a machine learning model from Aelien. 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 apache-2.0.

Checkpoints and train LMDBs from the 2026-08-30..09-03 debug of the three GPT-built visual-reasoning tasks in mianwu01/COF-maze (branch review/cof-6k-snapshot-20260825, commit fbee115). Code, configs, exact data-gener…

Downloads · 30 days

Access

Public

Updated Sep 3, 2026

Repo size

75.6 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt68.1 GB · 90%

At a glance

License: apache-2.0
Access: Public
Created: Sep 3, 2026
Updated: Sep 3, 2026
SHA: c4abfeee

Model card

From the Hugging Face model README

COF readiness-v3 artifacts (sliding / sudoku / tangram)

Checkpoints and train LMDBs from the 2026-08-30..09-03 debug of the three GPT-built visual-reasoning tasks in mianwu01/COF-maze (branch review/cof-6k-snapshot-20260825, commit fbee115). Code, configs, exact data-generation commands, evaluation summaries, and the full analysis live in that branch:

reports/2026-08-30_reasoning_readiness_debug.md — why the readiness gates failed and what fixes it
reports/2026-09-03_readiness_v3_cluster_handoff.md — how to restore and continue on a cluster
causal-forcing-changes/modifications.patch — trainer overlay incl. the remediation-v3 loss controls

All checkpoints are Wan2.1-T2V-1.3B causal (AR, I2V) Causal-Forcing generators, image_or_video_shape [1,21,16,60,104], trained with the v3 recipe from the public maze init Aelien/COF-maze-checkpoints/maze_ar_cont/checkpoint_model_001500. model.pt holds generator and generator_ema; trainer.pt (where present) adds optimizer/data/RNG state for exact resume.

path	what	dev8 result (seed 101)
`checkpoints/sudoku_maze_init_v3_long2/global_1985/{model,trainer}.pt`	sudoku 9x9 hidden-endpoint, exact-resume point	1/8 exact, 50% valid progress, givens 8/8
`checkpoints/sudoku_maze_init_v3_long2/global_1697/model.pt`	sudoku, best valid-progress model	1/8 exact, 63% valid progress, 50% legal
`checkpoints/sliding_maze_init_v3_x4/step_001200/{model,trainer}.pt`	sliding 3x3, 1024-sample run, resume point	evals pending
`checkpoints/sliding_maze_init_v3_long/step_000600/model.pt`	sliding 3x3, 256-sample measured peak	81% legal, 83% valid state, 4.6 moves
`data/reasoning_tasks/<task>/lmdb/train` (+ `sliding_exact_v1/lmdb/train1024`)	fp16 VAE latents (256 rows per task; 1024-row sliding set), action masks baked in	--

Configs: experiments/configs/{sudoku_maze_init_v3_long2,sliding_maze_init_v3_x4,sliding_maze_init_v3_long}.yaml. Evaluate with scripts/readiness_v3/eval_chain.sh; continue training with scripts/readiness_v3/run_segments.sh.

License: apache-2.0
Created: Sep 3, 2026
Updated: Sep 3, 2026