Model Selection

Reinforcement Learning Reward Model

# Reinforcement Learning Reward Model

Japanese Novel Reward Modernbert Ja 130m

A fine-tuned reward model based on modernbert-ja-130m for Japanese novel quality assessment, used to predict user ratings for novel texts.

Large Language Model

Transformers Japanese

Japanese Novel Reward Sarashina2.1 1b

A Japanese novel quality assessment model fine-tuned from sbintuitions/sarashina2.1-1b, used to predict user evaluations of novel texts.

Large Language Model

Transformers Japanese

Featured Recommended AI Models

AIbase

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

© 2025AIbase