Instructions to use kfdong/STP_model_Lean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kfdong/STP_model_Lean with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kfdong/STP_model_Lean")
model = AutoModelForCausalLM.from_pretrained("kfdong/STP_model_Lean", 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 kfdong/STP_model_Lean with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kfdong/STP_model_Lean

SGLang

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

Docker Model Runner
How to use kfdong/STP_model_Lean with Docker Model Runner:
```
docker model run hf.co/kfdong/STP_model_Lean
```

STP_model_Lean / README.md

kfdong

Update README.md

63a78b9 verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

1.51 kB

metadata

base_model:
  - deepseek-ai/DeepSeek-Prover-V1.5-SFT
datasets:
  - kfdong/STP_Lean
  - internlm/Lean-Workbook
license: mit
pipeline_tag: text-generation
library_name: transformers

This is the final Self-play Theorem Prover model as described in the paper https://arxiv.org/abs/2502.00212. The training and evalution code is avaliable here.

@article{dong2025beyond,
  title={Beyond Limited Data: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving},
  author={Dong, Kefan and Ma, Tengyu},
  journal={arXiv preprint arXiv:2502.00212},
  year={2025}
}

1. Evaluation Results

The table below compares the pass@3200 performance of STP (our model) and DeepSeek-Prover-V1.5 on miniF2F-test and ProofNet-test.

	miniF2F-test	ProofNet-test
DeepSeek-Prover-V1.5-SFT	53.3% ± 0.5%	21.0% ± 0.9%
DeepSeek-Prover-V1.5-RL	54.9% ± 0.7%	22.0% ± 0.5%
STP	61.7% ± 0.6%	23.1% ± 0.5%

2. Dataset

We also release the dataset here, which contains:

Extracted examples from mathlib4,
Generated correct proofs of statements in LeanWorkbook,
Generated correct proofs of conjectures proposed by our model during self-play training.

Our final model is finetuned from DeepSeek-Prover-V1.5-SFT with this dataset for 1 epoch.