menik1126
/

ovd-math-1-data-rlvr-step500

Model card Files Files and versions

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

RLVR baseline checkpoint

pi1, grpo, semantic step 500.

Historical pi1 pure GRPO; matches per-checkpoint evaluation provenance.

Pure GRPO/RLVR baseline (Teacher rejection disabled). This repository contains inference weights and tokenizer files, not optimizer state.

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including menik1126/ovd-math-1-data-rlvr-step500

OVD

OVD paper checkpoints: 1-data and 128-data training, Full response, High-entropy suffix, Random suffix, and RLVR baselines. • 21 items • Updated 6 minutes ago