Downloads · 30 days
0
arianraje/mimo-7b-gdn-opd-mathmix-h16k-probes
mimo-7b-gdn-opd-mathmix-h16k-probes is a machine learning model from arianraje. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Model-only probe snapshots from mimo-mathmix-h16k-runpod-1p2b-v1-20260829 (1B-1.2B OPD rung, DeepScaleR+DAPO mixture, horizon 16384). One subfolder per probe mark; each is a complete inference checkpoint (see its snap…
Downloads · 30 days
0
Access
Public
Updated Sep 6, 2026
Repo size
332 GB
Likes
0
Public
Click a slice to open those files.
.safetensors332 GB · 100%
From the Hugging Face model README
Model-only probe snapshots from mimo-mathmix-h16k-runpod-1p2b-v1-20260829
(1B->1.2B OPD rung, DeepScaleR+DAPO mixture, horizon 16384). One subfolder per
probe mark; each is a complete inference checkpoint (see its snapshot_meta.json)
plus the raw AIME24 eval outputs. Kept for retroactive evals (e.g. MATH-500).
Load with subfolder="probe-<mark>M".