Instructions to use purewhite42/DExplorer-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use purewhite42/DExplorer-8B with Transformers:

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

pipe = pipeline("text-generation", model="purewhite42/DExplorer-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("purewhite42/DExplorer-8B")
model = AutoModelForCausalLM.from_pretrained("purewhite42/DExplorer-8B")
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 purewhite42/DExplorer-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "purewhite42/DExplorer-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": "purewhite42/DExplorer-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/purewhite42/DExplorer-8B

SGLang

How to use purewhite42/DExplorer-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 "purewhite42/DExplorer-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": "purewhite42/DExplorer-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 "purewhite42/DExplorer-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": "purewhite42/DExplorer-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use purewhite42/DExplorer-8B with Docker Model Runner:
```
docker model run hf.co/purewhite42/DExplorer-8B
```

purewhite42 commited on Feb 28

Commit

5ffa9a8

verified ·

1 Parent(s): 55a1033

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -34,7 +34,7 @@ Please refer to the [📺GitHub repo](https://github.com/Purewhite2019/dexplorat
 **DExplorer-8B** is a Lean 4-based agent that generates provable formal mathematical statements through step-by-step **Deductive Exploration (DExploration)**. Instead of directly synthesizing problems in one shot, DExplorer explores the mathematical world step by step — introducing variables/hypotheses, deriving intermediate facts, and submitting conclusions — with each step verified by the Lean 4 kernel. This ensures the **provability** of generated statements while enabling the synthesis of **complex** problems that push the limits of state-of-the-art provers.
-This model is fine-tuned from [Goedel-Prover-V2-8B](https://huggingface.co/Goedel-Prover/Goedel-Prover-V2-8B) on [🤗purewhite42/DExploration_Dataset](https://huggingface.co/datasets/purewhite42/DExploration_Dataset) using supervised fine-tuning.
 ## ⚙️ Usage
@@ -73,7 +73,7 @@ For questions about the paper, data, or code:
 - **Issues**: [GitHub Issues](https://github.com/Purewhite2019/dexploration_main/issues)
 ## 👍 Acknowledgments
-- [NuminaMath-LEAN](https://huggingface.co/AI-MO/NuminaMath-LEAN) for the high-quality statement-proof data.
 - [Goedel-Prover](https://huggingface.co/Goedel-LM/Goedel-Prover-V2-8B) for the base model.
 - [Pantograph](https://github.com/leanprover/Pantograph) for Lean 4 interaction.
 - And many other open-source projects!

 **DExplorer-8B** is a Lean 4-based agent that generates provable formal mathematical statements through step-by-step **Deductive Exploration (DExploration)**. Instead of directly synthesizing problems in one shot, DExplorer explores the mathematical world step by step — introducing variables/hypotheses, deriving intermediate facts, and submitting conclusions — with each step verified by the Lean 4 kernel. This ensures the **provability** of generated statements while enabling the synthesis of **complex** problems that push the limits of state-of-the-art provers.
+This model is fine-tuned from [Goedel-Prover-V2-8B](https://huggingface.co/Goedel-LM/Goedel-Prover-V2-8B) on [DExploration-40K](https://huggingface.co/datasets/purewhite42/DExploration-40K) using supervised fine-tuning.
 ## ⚙️ Usage
 - **Issues**: [GitHub Issues](https://github.com/Purewhite2019/dexploration_main/issues)
 ## 👍 Acknowledgments
+- [NuminaMath-LEAN](https://huggingface.co/datasets/AI-MO/NuminaMath-LEAN) for the high-quality statement-proof data.
 - [Goedel-Prover](https://huggingface.co/Goedel-LM/Goedel-Prover-V2-8B) for the base model.
 - [Pantograph](https://github.com/leanprover/Pantograph) for Lean 4 interaction.
 - And many other open-source projects!