Instructions to use opendatalab/meta-rater-3b-25raters with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use opendatalab/meta-rater-3b-25raters with Transformers:

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

pipe = pipeline("text-generation", model="opendatalab/meta-rater-3b-25raters", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("opendatalab/meta-rater-3b-25raters", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use opendatalab/meta-rater-3b-25raters with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "opendatalab/meta-rater-3b-25raters"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "opendatalab/meta-rater-3b-25raters",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/opendatalab/meta-rater-3b-25raters

SGLang

How to use opendatalab/meta-rater-3b-25raters 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 "opendatalab/meta-rater-3b-25raters" \
    --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": "opendatalab/meta-rater-3b-25raters",
		"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 "opendatalab/meta-rater-3b-25raters" \
        --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": "opendatalab/meta-rater-3b-25raters",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use opendatalab/meta-rater-3b-25raters with Docker Model Runner:
```
docker model run hf.co/opendatalab/meta-rater-3b-25raters
```

Update license to Apache 2.0 and improve model card clarity

by nielsr HF Staff - opened Aug 9, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+15

-4

nielsr

Aug 9, 2025

This PR addresses two improvements for the model card:

License Update: The license in the model card metadata and content has been updated from MIT to Apache 2.0, as explicitly stated in the project's GitHub repository. This provides accurate licensing information for the model.
Content Refinements: Minor wording adjustments were made in the "Key Achievements" section to better reflect the paper's findings, and the GitHub star footer has been added to align with the project's official README.

Please review and merge this PR if everything looks good.

Update license to Apache 2.0 and improve model card clarity32e7e361

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment