Downloads · 30 days
19
38% of all-time downloads
Snowball-67B-A2B-10T-Mixed-RLVR2-Sync-Step116
open-athena/Snowball-67B-A2B-10T-Mixed-RLVR2-Sync-Step116
Snowball-67B-A2B-10T-Mixed-RLVR2-Sync-Step116 is a reinforcement learning model from open-athena. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
This is the Hugging Face export of optimizer checkpoint 116 from the September 11 Snowball synchronous mixed-domain RLVR lineage. RLVR1 was followed by RLVR2 without data shuffling. The arm used RLOO-N, the Megatron b…
All-time downloads
50
Public
Parameters
67.1B
134 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors134 GB · 100%
Parameter types
How the weights are stored.
BF1667.1B · 100%
Base models
Model card
From the Hugging Face model README
Snowball 67B-A2B — 10T Mixed RLVR2 sync step 116
This is the Hugging Face export of optimizer checkpoint 116 from the September 11 Snowball synchronous mixed-domain RLVR lineage. RLVR1 was followed by RLVR2 without data shuffling. The arm used RLOO-N, the Megatron backend, a 32K context window, batch size 512, and 16 rollouts per prompt on 64 H100s.
Checkpoint 118 was the true RLVR2 training-pass@16 peak at 0.63671875. It was removed by an earlier checkpoint pruning sweep, and the S3 bucket had no recoverable object version. Step 116 is the best complete retained checkpoint; its training pass@16 was 0.6171875, training reward was 0.67631429, and its 100-row holdout avg_score/pass@1 was 0.5275/0.44.
This checkpoint is a research artifact. RLVR2 validation did not improve over the stronger RLVR1 region.
We release our tools to the public with the intent that they are used safely, ethically, and responsibly. They are meant to contribute to the public's understanding of science, and aid in its advancement. By using this Marin model, you agree to comply with all applicable law.
- Task
- Reinforcement Learning
- Type
- grug_moe
- Created
- Sep 23, 2026
- Updated
- Oct 20, 2026