modular-ai/kantian-reward-model

Upload tokenizer

Reward model trained on 213 samples - 20251126-204442

Upload tokenizer

Reward model trained on 213 samples - 20251126-194928

Reward model trained on 213 samples - 20251126-192211

Reward model trained on 213 samples - 20251126-190902

Reward model trained on 203 samples - 20251126-160856

Reward model trained on 150 samples - 20251125-164654

Reward model trained on 101 samples - 20251124-173453

Reward model trained on 101 samples - 20251124-153532

Upload tokenizer

Reward model trained on 54 samples - 20251119-213559

initial commit