Instructions to use IAAR-Shanghai/xVerify-9B-C with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IAAR-Shanghai/xVerify-9B-C with Transformers:

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

pipe = pipeline("text-generation", model="IAAR-Shanghai/xVerify-9B-C", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("IAAR-Shanghai/xVerify-9B-C", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IAAR-Shanghai/xVerify-9B-C with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IAAR-Shanghai/xVerify-9B-C"
# 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-9B-C",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IAAR-Shanghai/xVerify-9B-C

SGLang

How to use IAAR-Shanghai/xVerify-9B-C 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-9B-C" \
    --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-9B-C",
		"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-9B-C" \
        --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-9B-C",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IAAR-Shanghai/xVerify-9B-C with Docker Model Runner:
```
docker model run hf.co/IAAR-Shanghai/xVerify-9B-C
```

nielsr HF Staff commited on Jan 1

Commit

3f63e9c

verified ·

1 Parent(s): 39d1b62

Add metadata and link to paper

Browse files

This PR improves the model card by:
- Adding `library_name: transformers` and `pipeline_tag: text-generation` to the YAML metadata. This enables the "Use in Transformers" button and improves discoverability.
- Adding a link to the research paper: [xVerify: Efficient Answer Verifier for Reasoning Model Evaluations](https://huggingface.co/papers/2504.10481).
- Including a paper badge in the header.

Cc: @Hush-cd @Duguce @deflinhec

Files changed (1) hide show

README.md +13 -6

README.md CHANGED Viewed

@@ -1,15 +1,17 @@
 ---
-inference: false
 language:
 - en
 - zh
 tags:
 - instruction-finetuning
 task_categories:
 - text-generation
-base_model:
-- THUDM/glm-4-9b-chat
-license: cc-by-nc-nd-4.0
 ---
 <h1 align="center">
@@ -24,10 +26,15 @@ license: cc-by-nc-nd-4.0
     <a href="https://huggingface.co/IAAR-Shanghai/xVerify-9B-C">
       <img src="https://img.shields.io/badge/🤗%20Hugging%20Face-xVerify--9B--C-yellow" alt="Hugging Face"/>
     </a>
   </div>
 </p>
-xVerify is an evaluation tool fine-tuned from a pre-trained large language model, designed specifically for objective questions with a single correct answer. It accurately extracts the final answer from lengthy reasoning processes and efficiently identifies equivalence across different forms of expressions.
 ---
@@ -60,4 +67,4 @@ Primarily handles Chinese and English responses while remaining compatible with
       journal={arXiv preprint arXiv:2504.10481},
       year={2025},
 }
-```

 ---
+base_model:
+- THUDM/glm-4-9b-chat
 language:
 - en
 - zh
+license: cc-by-nc-nd-4.0
 tags:
 - instruction-finetuning
+inference: false
 task_categories:
 - text-generation
+pipeline_tag: text-generation
+library_name: transformers
 ---
 <h1 align="center">
     <a href="https://huggingface.co/IAAR-Shanghai/xVerify-9B-C">
       <img src="https://img.shields.io/badge/🤗%20Hugging%20Face-xVerify--9B--C-yellow" alt="Hugging Face"/>
     </a>
+    <a href="https://huggingface.co/papers/2504.10481">
+      <img src="https://img.shields.io/badge/Paper-Arxiv-red" alt="Paper"/>
+    </a>
   </div>
 </p>
+xVerify is an evaluation tool fine-tuned from a pre-trained large language model, designed specifically for objective questions with a single correct answer. It was introduced in the paper [xVerify: Efficient Answer Verifier for Reasoning Model Evaluations](https://huggingface.co/papers/2504.10481).
+It accurately extracts the final answer from lengthy reasoning processes and efficiently identifies equivalence across different forms of expressions.
 ---
       journal={arXiv preprint arXiv:2504.10481},
       year={2025},
 }
+```