yyqoni
/

Phi-3-mini-4k-instruct-token-rm-700k

Text Classification

Model card Files Files and versions

This is the token-wise reward model introduced in the preprint Segmenting Text and Learning Their Rewards for Improved RLHF in Language Models (https://arxiv.org/abs/2501.02790). For more details, please visit our repository at https://github.com/yinyueqin/DenseRewardRLHF-PPO.

Downloads last month: 3

Safetensors

Model size

4B params

Tensor type

BF16

·

Model tree for yyqoni/Phi-3-mini-4k-instruct-token-rm-700k

Base model

microsoft/Phi-3-mini-4k-instruct

Finetuned

(853)

this model

Dataset used to train yyqoni/Phi-3-mini-4k-instruct-token-rm-700k

Collection including yyqoni/Phi-3-mini-4k-instruct-token-rm-700k

DenseRewardRLHF-PPO

This repository contains the released models for our paper Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model. • 18 items • Updated Jan 11, 2025 • 1

Paper for yyqoni/Phi-3-mini-4k-instruct-token-rm-700k

Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model

Paper • 2501.02790 • Published Jan 6, 2025 • 8