Instructions to use luzimu/WebGenAgent-LM-8B-Step-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luzimu/WebGenAgent-LM-8B-Step-GRPO with Transformers:

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

pipe = pipeline("image-text-to-text", model="luzimu/WebGenAgent-LM-8B-Step-GRPO")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("luzimu/WebGenAgent-LM-8B-Step-GRPO")
model = AutoModelForCausalLM.from_pretrained("luzimu/WebGenAgent-LM-8B-Step-GRPO")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
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 luzimu/WebGenAgent-LM-8B-Step-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "luzimu/WebGenAgent-LM-8B-Step-GRPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luzimu/WebGenAgent-LM-8B-Step-GRPO",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/luzimu/WebGenAgent-LM-8B-Step-GRPO

SGLang

How to use luzimu/WebGenAgent-LM-8B-Step-GRPO 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 "luzimu/WebGenAgent-LM-8B-Step-GRPO" \
    --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": "luzimu/WebGenAgent-LM-8B-Step-GRPO",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "luzimu/WebGenAgent-LM-8B-Step-GRPO" \
        --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": "luzimu/WebGenAgent-LM-8B-Step-GRPO",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use luzimu/WebGenAgent-LM-8B-Step-GRPO with Docker Model Runner:
```
docker model run hf.co/luzimu/WebGenAgent-LM-8B-Step-GRPO
```

Improve model card: Add pipeline tag, library name, and GitHub link

by nielsr HF Staff - opened Sep 30, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+15

-11

Files changed (1) hide show

README.md +15 -11

README.md CHANGED Viewed

@@ -1,16 +1,20 @@
 ---
-license: mit
 datasets:
 - luzimu/webgen-agent_train_step-grpo
 - luzimu/webgen-agent_train_sft
-base_model:
-- Qwen/Qwen3-8B
 ---
 # WebGen-Agent
 WebGen-Agent is an advanced website generation agent designed to autonomously create websites from natural language instructions. It was introduced in the paper [WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning](https://arxiv.org/pdf/2509.22644v1).
 ## Project Overview
 WebGen-Agent combines state-of-the-art language models with specialized training techniques to create a powerful website generation tool. The agent can understand natural language instructions specifying appearance and functional requirements, iteratively generate website codebases, and refine them using visual and functional feedback.
@@ -35,25 +39,25 @@ Links to the data and model parameters are as follows:
 WebGen-Agent follows an iterative, multi-step paradigm for website generation:
-1. **Code Generation**: The agent generates code to create or edit website files based on natural language instructions
-2. **Code Execution**: Dependencies are installed and the website service is started
-3. **Feedback Gathering**:
    - A screenshot of the website is captured
    - A Visual Language Model (VLM) provides appearance feedback and scores
    - A GUI-agent tests the website functionality and provides functional feedback
-4. **Refinement**: Based on the feedback, the agent continues to improve the website until it meets requirements
-![WebGen-Agent Workflow](fig/webgen-agent.png)
 ## Step-GRPO with Screenshot and GUI-agent Feedback
 The Step-GRPO with Screenshot and GUI-agent Feedback approach uses the screenshot and GUI-agent scores inherently produced in the WebGen-Agent workflow as step-level rewards:
-- **Screenshot Score**: Quantifies the visual appeal and aesthetics of the website
-- **GUI-agent Score**: Measures how well the website meets functional requirements
 These dual rewards provide dense, reliable process supervision that significantly improves the model's ability to generate high-quality websites.
-![Step-GRPO with Screenshot and GUI-agent Feedback](fig/step-grpo.png)
 ## Citation

 ---
+base_model:
+- Qwen/Qwen3-8B
 datasets:
 - luzimu/webgen-agent_train_step-grpo
 - luzimu/webgen-agent_train_sft
+license: mit
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 # WebGen-Agent
 WebGen-Agent is an advanced website generation agent designed to autonomously create websites from natural language instructions. It was introduced in the paper [WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning](https://arxiv.org/pdf/2509.22644v1).
+Code: https://github.com/mnluzimu/WebGen-Agent
 ## Project Overview
 WebGen-Agent combines state-of-the-art language models with specialized training techniques to create a powerful website generation tool. The agent can understand natural language instructions specifying appearance and functional requirements, iteratively generate website codebases, and refine them using visual and functional feedback.
 WebGen-Agent follows an iterative, multi-step paradigm for website generation:
+1.  **Code Generation**: The agent generates code to create or edit website files based on natural language instructions
+2.  **Code Execution**: Dependencies are installed and the website service is started
+3.  **Feedback Gathering**:
    - A screenshot of the website is captured
    - A Visual Language Model (VLM) provides appearance feedback and scores
    - A GUI-agent tests the website functionality and provides functional feedback
+4.  **Refinement**: Based on the feedback, the agent continues to improve the website until it meets requirements
+![WebGen-Agent Workflow](https://github.com/mnluzimu/WebGen-Agent/raw/main/paper/webgen-agent.png)
 ## Step-GRPO with Screenshot and GUI-agent Feedback
 The Step-GRPO with Screenshot and GUI-agent Feedback approach uses the screenshot and GUI-agent scores inherently produced in the WebGen-Agent workflow as step-level rewards:
+-   **Screenshot Score**: Quantifies the visual appeal and aesthetics of the website
+-   **GUI-agent Score**: Measures how well the website meets functional requirements
 These dual rewards provide dense, reliable process supervision that significantly improves the model's ability to generate high-quality websites.
+![Step-GRPO with Screenshot and GUI-agent Feedback](https://github.com/mnluzimu/WebGen-Agent/raw/main/paper/step-grpo.png)
 ## Citation