Instructions to use rubricreward/R3-Qwen3-14B-4k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rubricreward/R3-Qwen3-14B-4k with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="rubricreward/R3-Qwen3-14B-4k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rubricreward/R3-Qwen3-14B-4k")
model = AutoModelForCausalLM.from_pretrained("rubricreward/R3-Qwen3-14B-4k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rubricreward/R3-Qwen3-14B-4k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rubricreward/R3-Qwen3-14B-4k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rubricreward/R3-Qwen3-14B-4k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rubricreward/R3-Qwen3-14B-4k

SGLang

How to use rubricreward/R3-Qwen3-14B-4k 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 "rubricreward/R3-Qwen3-14B-4k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rubricreward/R3-Qwen3-14B-4k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "rubricreward/R3-Qwen3-14B-4k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rubricreward/R3-Qwen3-14B-4k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rubricreward/R3-Qwen3-14B-4k with Docker Model Runner:
```
docker model run hf.co/rubricreward/R3-Qwen3-14B-4k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

R3-Qwen3-14B-4k

R3-Qwen3-14B-4k is part of the R3 family, a series of Robust Rubric-Agnostic Reward Models. We perform SFT on the Qwen3 model family on the 4B, 8B, and 14B scales as well as on Phi-4-reasoning plus. Check out our paper for more information!

Model description

Model type: A reward model trained on a curated R3 dataset collected from 45 diverse sources that covers tasks such as classification, preference optimization, and question answering. Each example in the dataset contains an instruction and task description, input, response(s), evaluation rubrics, and a score along with the corresponding reasoning.
Language(s) (NLP): English
License: Apache 2.0
Finetuned from model: Qwen/Qwen3-14B

Model Sources

Project Page: https://rubricreward.github.io
Repository: https://github.com/rubricreward/r3
Paper: https://arxiv.org/abs/2505.13388

Using the Model

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

model_path = "rubricreward/R3-Qwen3-14B-4k"
tokenizer = AutoTokenizer.from_pretrained(model_path)
sampling_params = SamplingParams(temperature=0.6, top_p=0.95, max_tokens=8192, min_p=0, top_k=20)

llm = LLM(
  model=model_path,
  dtype="bfloat16",
  max_model_len=10000,
  tensor_parallel_size=2,
  gpu_memory_utilization=0.9,
  enforce_eager=True,
)

messages: list[dict[str, str]] = [
  {'content': "Evaluate the response based on the given task, input, response, and evaluation rubric. Provide a fair and detailed assessment following the rubric...", 'role': 'user'}
]

list_text = tokenizer.apply_chat_template(
  messages,
  tokenize=False,
  add_generation_prompt=True,
  enable_thinking=True # Switch between thinking and non-thinking modes. 
)

outputs = llm.generate(list_text, sampling_params)

License and use

R3 is licensed under the Apache 2.0 license.

Citation

@article{anugraha2025r3,
  title={R3: Robust Rubric-Agnostic Reward Models},
  author={Anugraha, David and Tang, Zilu and Miranda, Lester James V. and Zhao, Hanyang and Farhansyah, Mohammad Rifqi and Kuwanto, Garry and Wijaya, Derry and Winata, Genta Indra},
  journal={arXiv preprint arXiv:2505.13388},
  year={2025}
}