OVD
Collection
OVD paper checkpoints: 1-data and 128-data training, Full response, High-entropy suffix, Random suffix, and RLVR baselines. • 33 items • Updated
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Historical OVD checkpoint
pi1, grpo, semantic step 300.
Fresh pi1 pure GRPO retraining 2026-09-12; successful subsequent evaluation; not the missing historical step300.
Historical evaluated weights, not the recently repaired implementation. This repository contains inference weights and tokenizer files, not optimizer state.
- Downloads last month
- 11
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support