AnonyRepo
/

ormprotocol-bidir-lasttoken-s42

process-reward-model

discrete-diffusion

Model card Files Files and versions

ormprotocol-bidir-lasttoken

ORM-protocol Bidir LoRA with last-token pooling (seed 42). Final accuracy = 0.919. Counterpart to the causal variant for Appendix G decision tree.

Downloads last month: -

Inference Providers NEW

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

Model tree for AnonyRepo/ormprotocol-bidir-lasttoken-s42

Base model

Dream-org/Dream-v0-Instruct-7B

Adapter

(13)

this model