Align model card with released pipeline

README.md

@@ -16,15 +16,18 @@ tags:
 
 # RARE-Task-Level
 
-This private repository contains the final **task-level adaptive rubric**
+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.
 
-[[Paper](https://openreview.net/forum?id=XgYh8jfypi)]
-[[Dataset](https://huggingface.co/datasets/EurekaTian/RARE)]
-[[Code](https://github.com/Eureka-Maggie/RARE)]
+<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 |
 |---|---|---:|
@@ -36,21 +39,13 @@ 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 full `transformers` checkpoint derived from
-`Qwen/Qwen3-4B-Instruct-2507`. Load a variant with:
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-repo_id = "EurekaTian/RARE-Task-Level"
-variant = "2d_animation"
-tokenizer = AutoTokenizer.from_pretrained(repo_id, subfolder=variant)
-model = AutoModelForCausalLM.from_pretrained(
-    repo_id, subfolder=variant, device_map="auto", torch_dtype="auto"
-)
-```
-
-Use the corresponding configuration from `EurekaTian/RARE` for the released
-system instruction and query format. The weights are licensed under Apache-2.0;
+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.