Instructions to use IAAR-Shanghai/xVerify-32B-I with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IAAR-Shanghai/xVerify-32B-I with Transformers:

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

pipe = pipeline("text-generation", model="IAAR-Shanghai/xVerify-32B-I")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("IAAR-Shanghai/xVerify-32B-I")
model = AutoModelForCausalLM.from_pretrained("IAAR-Shanghai/xVerify-32B-I")
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 IAAR-Shanghai/xVerify-32B-I with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IAAR-Shanghai/xVerify-32B-I"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IAAR-Shanghai/xVerify-32B-I",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IAAR-Shanghai/xVerify-32B-I

SGLang

How to use IAAR-Shanghai/xVerify-32B-I 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 "IAAR-Shanghai/xVerify-32B-I" \
    --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": "IAAR-Shanghai/xVerify-32B-I",
		"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 "IAAR-Shanghai/xVerify-32B-I" \
        --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": "IAAR-Shanghai/xVerify-32B-I",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IAAR-Shanghai/xVerify-32B-I with Docker Model Runner:
```
docker model run hf.co/IAAR-Shanghai/xVerify-32B-I
```

Add pipeline_tag, library_name and link to paper

by nielsr HF Staff - opened Jan 1

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+70

-60

nielsr

Jan 1

Hi! I'm Niels, part of the Hugging Face community science team.

This PR improves the model card for xVerify-32B-I by:

Adding library_name: transformers and pipeline_tag: text-generation to the metadata for better discoverability and to enable the "Use in Transformers" button.
Linking the model to the original research paper xVerify: Efficient Answer Verifier for Reasoning Model Evaluations via the arxiv tag and a direct link.
Refining the metadata structure.

Please let me know if you have any questions!

Add pipeline_tag, library_name and link to papercb936155

apocryphal

Memtensor Research Group org Jan 1

Hi Niels, thanks a lot for the PR and for the detailed improvements! 🙏

These additions make the model card much clearer and more discoverable on the Hub. The metadata updates, paper reference, and GitHub link are all very helpful for users.

I'm happy to accept these changes and will merge the PR shortly. Thanks again for your contribution and for the support from the Hugging Face community team!

apocryphal changed pull request status to merged Jan 1

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