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

Libraries

How to use openbmb/MathForm-8B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openbmb/MathForm-8B")
model = AutoModelForCausalLM.from_pretrained("openbmb/MathForm-8B", 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 openbmb/MathForm-8B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/openbmb/MathForm-8B

SGLang

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

Docker Model Runner
How to use openbmb/MathForm-8B with Docker Model Runner:
```
docker model run hf.co/openbmb/MathForm-8B
```

daypu commited on 2 days ago

Commit

3d17320

1 Parent(s): 9a828a5

update readme: add arXiv and GitHub links, update citation

Browse files

Files changed (2) hide show

README.md +11 -7
README_zh.md +11 -7

README.md CHANGED Viewed

@@ -21,8 +21,8 @@ tags:
 </div>
 <p align="center">
-  <img src="https://img.shields.io/badge/Paper-arXiv-b31b1b.svg" alt="Paper">
-  <a href="[GITHUB_URL]"><img src="https://img.shields.io/badge/GitHub-MathForm-181717.svg" alt="Code"></a>
   <a href="https://huggingface.co/datasets/openbmb/FormalVerse"><img src="https://img.shields.io/badge/🤗%20Dataset-FormalVerse-yellow.svg" alt="FormalVerse Dataset"></a>
 </p>
@@ -112,7 +112,7 @@ Both servers expose an OpenAI-compatible API at
 ## Evaluation
 The evaluation pipeline, benchmark files, and Pass@k scripts are available in
-the [MathForm repository]([GITHUB_URL]). Compilation checks require a running
 Kimina Lean Server. The experiments use Lean 4.21.0.
 ## License
@@ -122,9 +122,13 @@ This project is licensed under the Apache License 2.0.
 ## Citation
 ```bibtex
-@misc{pu2026mathform,
-  title  = {MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement},
-  author = {Lushi Pu and Weiming Zhang and Xinheng Xie and Zixuan Fu and Bingxiang He and Hengyu Zhao and Hongya Lyu and Xin Li and Jie Zhou and Yudong Wang},
-  year   = {2026}
 }
 ```

 </div>
 <p align="center">
+  <a href="https://arxiv.org/abs/2608.14221"><img src="https://img.shields.io/badge/Paper-arXiv-b31b1b.svg" alt="Paper"></a>
+  <a href="https://github.com/OpenBMB/MathForm"><img src="https://img.shields.io/badge/GitHub-MathForm-181717.svg" alt="Code"></a>
   <a href="https://huggingface.co/datasets/openbmb/FormalVerse"><img src="https://img.shields.io/badge/🤗%20Dataset-FormalVerse-yellow.svg" alt="FormalVerse Dataset"></a>
 </p>
 ## Evaluation
 The evaluation pipeline, benchmark files, and Pass@k scripts are available in
+the [MathForm repository](https://github.com/OpenBMB/MathForm). Compilation checks require a running
 Kimina Lean Server. The experiments use Lean 4.21.0.
 ## License
 ## Citation
 ```bibtex
+@misc{pu2026mathformscalingmathematicalautoformalization,
+      title={MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement},
+      author={Lushi Pu and Weiming Zhang and Xinheng Xie and Zixuan Fu and Bingxiang He and Hengyu Zhao and Hongya Lyu and Xin Li and Jie Zhou and Yudong Wang},
+      year={2026},
+      eprint={2608.14221},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI},
+      url={https://arxiv.org/abs/2608.14221},
 }
 ```

README_zh.md CHANGED Viewed

@@ -3,8 +3,8 @@
 </div>
 <p align="center">
-  <img src="https://img.shields.io/badge/Paper-arXiv-b31b1b.svg" alt="论文">
-  <a href="[GITHUB_URL]"><img src="https://img.shields.io/badge/GitHub-MathForm-181717.svg" alt="代码"></a>
   <a href="https://huggingface.co/datasets/openbmb/FormalVerse"><img src="https://img.shields.io/badge/🤗%20Dataset-FormalVerse-yellow.svg" alt="FormalVerse 数据集"></a>
 </p>
@@ -88,7 +88,7 @@ OpenAI 的 API。
 ## 评测
-评测流程、基准文件和 Pass@k 脚本位于 [MathForm 仓库]([GITHUB_URL])。编译检查需要运行 Kimina Lean Server。实验使用 Lean 4.21.0。
 ## 许可证
@@ -97,9 +97,13 @@ OpenAI 的 API。
 ## 引用
 ```bibtex
-@misc{pu2026mathform,
-  title  = {MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement},
-  author = {Lushi Pu and Weiming Zhang and Xinheng Xie and Zixuan Fu and Bingxiang He and Hengyu Zhao and Hongya Lyu and Xin Li and Jie Zhou and Yudong Wang},
-  year   = {2026}
 }
 ```

 </div>
 <p align="center">
+  <a href="https://arxiv.org/abs/2608.14221"><img src="https://img.shields.io/badge/Paper-arXiv-b31b1b.svg" alt="论文"></a>
+  <a href="https://github.com/OpenBMB/MathForm"><img src="https://img.shields.io/badge/GitHub-MathForm-181717.svg" alt="代码"></a>
   <a href="https://huggingface.co/datasets/openbmb/FormalVerse"><img src="https://img.shields.io/badge/🤗%20Dataset-FormalVerse-yellow.svg" alt="FormalVerse 数据集"></a>
 </p>
 ## 评测
+评测流程、基准文件和 Pass@k 脚本位于 [MathForm 仓库](https://github.com/OpenBMB/MathForm)。编译检查需要运行 Kimina Lean Server。实验使用 Lean 4.21.0。
 ## 许可证
 ## 引用
 ```bibtex
+@misc{pu2026mathformscalingmathematicalautoformalization,
+      title={MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement},
+      author={Lushi Pu and Weiming Zhang and Xinheng Xie and Zixuan Fu and Bingxiang He and Hengyu Zhao and Hongya Lyu and Xin Li and Jie Zhou and Yudong Wang},
+      year={2026},
+      eprint={2608.14221},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI},
+      url={https://arxiv.org/abs/2608.14221},
 }
 ```