Instructions to use cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench with Transformers:

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

pipe = pipeline("text-generation", model="cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench")
model = AutoModelForCausalLM.from_pretrained("cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench

SGLang

How to use cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench 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 "cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench" \
    --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": "cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench",
		"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 "cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench" \
        --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": "cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench with Docker Model Runner:
```
docker model run hf.co/cx-cmu/AutoGEO_mini_Qwen1.7B_GEOBench
```

yujiangw commited on Dec 17, 2025

Commit

e708893

verified ·

1 Parent(s): 45f3cba

Create README.md

Browse files

Files changed (1) hide show

README.md +50 -0

README.md ADDED Viewed

	@@ -0,0 +1,50 @@

+---
+license: mit
+language:
+- en
+tags:
+- text-rewriting
+- web
+- generative-engine-optimization
+- geo
+- reinforcement-learning
+- grpo
+- qwen3
+- transformers
+- safetensors
+library_name: transformers
+pipeline_tag: text-generation
+base_model: Qwen/Qwen3-1.7B
+---
+# AutoGEO_mini_Qwen1.7B_GEOBench
+A lightweight **web-document rewriting** model fine-tuned with **GRPO** (reinforcement learning) from **Qwen3-1.7B**, developed as part of the AutoGEO framework introduced in:
+**WHAT GENERATIVE SEARCH ENGINES LIKE AND HOW TO OPTIMIZE WEB CONTENT COOPERATIVELY**
+Paper (arXiv): https://arxiv.org/abs/2510.11438
+---
+## What this model does
+**AutoGEO_mini_Qwen1.7B_GEOBench** rewrites raw web documents into improved versions that are better aligned with generative search engines’ preferences for **GEO-Bench dataset**.
+In our experiments/usage:
+- The total cost is about **0.0071×** the cost of **gemini-2.5-pro** for comparable rewriting workloads.
+- Rewritten documents achieve **significant improvements in GEO metrics**.
+---
+## Training summary
+- **Base model:** Qwen3-1.7B
+- **Method:** GRPO-based reinforcement learning fine-tuning
+- **Task:** Rewrite original web documents to improve GEO metrics (per the AutoGEO framework in the paper above)
+---
+## Repository contents
+This repository includes the standard inference artifacts (e.g., `model.safetensors`, `config.json`, `tokenizer.json`, `chat_template.jinja`, etc.) required to load and run the model with `transformers`.
+---