Instructions to use OpenRubrics/ReVeR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenRubrics/ReVeR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OpenRubrics/ReVeR")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenRubrics/ReVeR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use OpenRubrics/ReVeR with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenRubrics/ReVeR" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenRubrics/ReVeR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/OpenRubrics/ReVeR
- SGLang
How to use OpenRubrics/ReVeR with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "OpenRubrics/ReVeR" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenRubrics/ReVeR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "OpenRubrics/ReVeR" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenRubrics/ReVeR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use OpenRubrics/ReVeR with Docker Model Runner:
docker model run hf.co/OpenRubrics/ReVeR
Add citation
Browse files
README.md
CHANGED
|
@@ -157,3 +157,19 @@ rubric = text[text.rfind("<rubric>") + len("<rubric>"):text.rfind("</rubric>")].
|
|
| 157 |
## Versions
|
| 158 |
|
| 159 |
Tested with vLLM 0.18.0, Transformers 5.12.1, PyTorch 2.10.0 and the `openai` client 2.24.0. The checkpoints were saved with Transformers 5.12.1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 157 |
## Versions
|
| 158 |
|
| 159 |
Tested with vLLM 0.18.0, Transformers 5.12.1, PyTorch 2.10.0 and the `openai` client 2.24.0. The checkpoints were saved with Transformers 5.12.1.
|
| 160 |
+
|
| 161 |
+
## Citation
|
| 162 |
+
|
| 163 |
+
If you use these models, please cite our paper [Rubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges](https://arxiv.org/abs/2610.18766):
|
| 164 |
+
|
| 165 |
+
```bibtex
|
| 166 |
+
@misc{liu2026rubricstaskverdictsevidence,
|
| 167 |
+
title={Rubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges},
|
| 168 |
+
author={Tianci Liu and Haoyu Wang},
|
| 169 |
+
year={2026},
|
| 170 |
+
eprint={2610.18766},
|
| 171 |
+
archivePrefix={arXiv},
|
| 172 |
+
primaryClass={cs.CL},
|
| 173 |
+
url={https://arxiv.org/abs/2610.18766},
|
| 174 |
+
}
|
| 175 |
+
```
|