Downloads · 30 days
0
dureduck/gemma4-26b-a4b-gsm8k-grpo-stopturn4096-20260922
gemma4-26b-a4b-gsm8k-grpo-stopturn4096-20260922 is a machine learning model from dureduck. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Full native Orbax training checkpoints. Each version includes model parameters, optimizer state, native metadata, and a resume manifest. Checkpoint upload integrity is distinct from restore verification.
Downloads · 30 days
0
Access
Public
Updated Sep 23, 2026
Repo size
235 GB
Likes
0
Public
Click a slice to open those files.
Other235 GB · 100%
From the Hugging Face model README
Full native Orbax training checkpoints. Each version includes model parameters, optimizer state, native metadata, and a resume manifest. Checkpoint upload integrity is distinct from restore verification.