Instructions to use OpenRubrics/RubricARROW-8B-Rubric with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenRubrics/RubricARROW-8B-Rubric with Transformers:

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

pipe = pipeline("text-generation", model="OpenRubrics/RubricARROW-8B-Rubric")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenRubrics/RubricARROW-8B-Rubric")
model = AutoModelForCausalLM.from_pretrained("OpenRubrics/RubricARROW-8B-Rubric", device_map="auto")
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 Settings

vLLM

How to use OpenRubrics/RubricARROW-8B-Rubric with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenRubrics/RubricARROW-8B-Rubric"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenRubrics/RubricARROW-8B-Rubric",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenRubrics/RubricARROW-8B-Rubric

SGLang

How to use OpenRubrics/RubricARROW-8B-Rubric 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/RubricARROW-8B-Rubric" \
    --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": "OpenRubrics/RubricARROW-8B-Rubric",
		"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 "OpenRubrics/RubricARROW-8B-Rubric" \
        --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": "OpenRubrics/RubricARROW-8B-Rubric",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenRubrics/RubricARROW-8B-Rubric with Docker Model Runner:
```
docker model run hf.co/OpenRubrics/RubricARROW-8B-Rubric
```

Add metadata and link to paper

by nielsr HF Staff - opened May 30

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+59

-26

nielsr

May 30

Hi! I'm opening this pull request to improve the model card for RubricARROW-8B-Rubric.

Specifically, I've:

Added library_name, pipeline_tag, and base_model metadata.
Linked the model to its research paper: RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains.
Maintained the provided usage instructions and citation.

This will help users discover the model more easily and provide context regarding its architecture and training.

Add metadata and link to paper17fbd0b2

Dazzlinglights changed pull request status to merged May 30

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment