| --- |
| license: apache-2.0 |
| language: |
| - zh |
| library_name: transformers |
| pipeline_tag: text-generation |
| base_model: Qwen/Qwen3-4B-Instruct-2507 |
| datasets: |
| - EurekaTian/RARE |
| tags: |
| - reinforcement-learning |
| - grpo |
| - adaptive-rubric |
| - script-generation |
| --- |
| |
| # RARE-Task-Level |
|
|
| This repository contains the final **task-level adaptive rubric** |
| checkpoints from **RARE: Reinforcement Learning with Adaptive Rubric Evolution for Open-Ended Generation**. |
| Within each production style, all queries share a six-criterion rubric that is |
| periodically revised from cross-query on-policy evidence while preserving its |
| IDs, order, score maxima, and reward aggregation. |
|
|
| <p align="center"> |
| <a href="https://eureka-maggie.github.io/RARE/"><img src="https://img.shields.io/badge/Project-Page-52735C?style=flat-square" alt="Project page" /></a> |
| <a href="https://openreview.net/forum?id=XgYh8jfypi"><img src="https://img.shields.io/badge/Paper-OpenReview-B31B1B?style=flat-square" alt="Paper" /></a> |
| <a href="https://github.com/Eureka-Maggie/RARE"><img src="https://img.shields.io/badge/Code-GitHub-181717?style=flat-square&logo=github" alt="Code" /></a> |
| <a href="https://huggingface.co/datasets/EurekaTian/RARE"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Dataset-RARE-FFD21E?style=flat-square" alt="Dataset" /></a> |
| </p> |
|
|
| | Subfolder | Production style | Final RL step | |
| |---|---|---:| |
| | `2d_animation` | 2D animation | 132 | |
| | `3d_stopmotion` | 3D and stop-motion animation | 108 | |
| | `live_action` | Live action | 94 | |
|
|
| The held-out scores are 76.27, 75.56, and 69.84 for the three styles, |
| respectively, for an equally weighted average of **73.89**. This is a 1.08-point |
| gain over the matched Task-Static baseline. |
|
|
| Each subfolder is an independent inference-only full checkpoint derived from |
| `Qwen/Qwen3-4B-Instruct-2507`; optimizer and trainer state are not included. |
| The exact launcher and settings are documented in the |
| [RARE repository](https://github.com/Eureka-Maggie/RARE#training). Use the |
| corresponding configuration from [EurekaTian/RARE](https://huggingface.co/datasets/EurekaTian/RARE) |
| for the released system instruction and query format. This card does not add a |
| separate convenience inference command that was not part of the released |
| pipeline. The weights are licensed under Apache-2.0; |
| the dataset is separately licensed under CC BY 4.0. The canonical paper citation |
| will be added after publication metadata is finalized. |
|
|
