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
```

nielsr HF Staff commited on Jun 9, 2025

Commit

596e9f8

verified ·

1 Parent(s): 4606ce8

Add pipeline_tag and library_name + project and github URL + trust_remote_code=True

Browse files

This PR adds the `pipeline_tag` and `library_name` to the model card's metadata, enhancing discoverability and usability. It also includes the project and github URL, and adds `trust_remote_code=True` to the usage example.

Files changed (1) hide show

README.md +8 -4

README.md CHANGED Viewed

@@ -1,9 +1,11 @@
 ---
-license: mit
 datasets:
 - cerebras/SlimPajama-627B
 language:
 - en
 ---
 # Meta-rater Language Model (3.3B Parameters, 100B Tokens)
@@ -96,8 +98,8 @@ import torch
 # Load model and tokenizer
 model_name = "opendatalab/meta-rater-3b-25raters"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
 # Generate text (optimized for high-quality output)
 prompt = "The key principles of sustainable development include"
@@ -188,6 +190,8 @@ If you use this model in your research, please cite:
 - **PRRC Rating Models**: Quality assessment models used for data selection
 - **Annotated SlimPajama**: Complete dataset with quality scores
 - **Random Baselines**: Corresponding baseline models for comparison
 ## License
@@ -195,4 +199,4 @@ Please refer to the license terms of the original SlimPajama dataset and follow
 ## Contact
-For questions or issues, please contact the authors or open an issue in the repository.

 ---
 datasets:
 - cerebras/SlimPajama-627B
 language:
 - en
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
 ---
 # Meta-rater Language Model (3.3B Parameters, 100B Tokens)
 # Load model and tokenizer
 model_name = "opendatalab/meta-rater-3b-25raters"
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
 # Generate text (optimized for high-quality output)
 prompt = "The key principles of sustainable development include"
 - **PRRC Rating Models**: Quality assessment models used for data selection
 - **Annotated SlimPajama**: Complete dataset with quality scores
 - **Random Baselines**: Corresponding baseline models for comparison
+- **Project Page**: [Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models](https://huggingface.co/papers/2504.14194)
+- **Github**: [Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models](https://github.com/opendatalab/Meta-rater)
 ## License
 ## Contact
+For questions or issues, please contact the authors or open an issue in the repository.