Instructions to use GuoxinChen/ReForm-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GuoxinChen/ReForm-32B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GuoxinChen/ReForm-32B")
model = AutoModelForCausalLM.from_pretrained("GuoxinChen/ReForm-32B")
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 GuoxinChen/ReForm-32B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GuoxinChen/ReForm-32B

SGLang

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

Docker Model Runner
How to use GuoxinChen/ReForm-32B with Docker Model Runner:
```
docker model run hf.co/GuoxinChen/ReForm-32B
```

nielsr HF Staff commited on Oct 31, 2025

Commit

1ca31eb

verified ·

1 Parent(s): 464c7c0

Add pipeline tag and library name to model card

Browse files

This PR improves the model card by adding the `pipeline_tag: text-generation` and `library_name: transformers` to its metadata.

- The `pipeline_tag` ensures the model is discoverable under text generation tasks on the Hugging Face Hub.
- The `library_name` enables the automated "how to use" widget, providing convenient code snippets for users, as the model explicitly uses `transformers` in its quick start guide.

All existing content, including links to the paper and code, remains unchanged.

Files changed (1) hide show

README.md +8 -4

README.md CHANGED Viewed

@@ -1,10 +1,13 @@
 ---
-license: apache-2.0
-language:
-- en
 base_model:
 - Qwen/Qwen3-8B
 ---
 <div align="center">
 # 🧩 ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization
@@ -50,7 +53,8 @@ model_name = "GuoxinChen/ReForm-8B"  # or "GuoxinChen/ReForm-32B"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
-prompt = "Think step by step to translate the mathematical problem in natural language to Lean 4, and verify the consistency.\nLet $a_1, a_2,\\cdots, a_n$ be real constants, $x$ a real variable, and $f(x)=\\cos(a_1+x)+\\frac{1}{2}\\cos(a_2+x)+\\frac{1}{4}\\cos(a_3+x)+\\cdots+\\frac{1}{2^{n-1}}\\cos(a_n+x).$ Given that $f(x_1)=f(x_2)=0,$ prove that $x_2-x_1=m\\pi$ for some integer $m.$"
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 outputs = model.generate(**inputs, max_new_tokens=512)

 ---
 base_model:
 - Qwen/Qwen3-8B
+language:
+- en
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
 ---
 <div align="center">
 # 🧩 ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
+prompt = "Think step by step to translate the mathematical problem in natural language to Lean 4, and verify the consistency.
+Let $a_1, a_2,\\cdots, a_n$ be real constants, $x$ a real variable, and $f(x)=\\cos(a_1+x)+\\frac{1}{2}\\cos(a_2+x)+\\frac{1}{4}\\cos(a_3+x)+\\cdots+\\frac{1}{2^{n-1}}\\cos(a_n+x).$ Given that $f(x_1)=f(x_2)=0,$ prove that $x_2-x_1=m\\pi$ for some integer $m.$"
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 outputs = model.generate(**inputs, max_new_tokens=512)