from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "luzimu/WebGen-LM-32B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "user", "content": "Write HTML, CSS, and JavaScript for a simple to-do list web application. The list should allow users to add and remove items."},
]

chat_input = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

model_inputs = tokenizer([chat_input], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=2048,
    do_sample=True,
    temperature=0.7,
    top_p=0.95
)

# Decode only the newly generated tokens
output_text = tokenizer.decode(generated_ids[0][model_inputs.input_ids.shape[1]:], skip_special_tokens=False)
print(output_text)

Performance on WebGen-Bench

Citation

If you find our project useful, please cite:

@misc{lu2025webgenbenchevaluatingllmsgenerating,
      title={WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch}, 
      author={Zimu Lu and Yunqiao Yang and Houxing Ren and Haotian Hou and Han Xiao and Ke Wang and Weikang Shi and Aojun Zhou and Mingjie Zhan and Hongsheng Li},
      year={2025},
      eprint={2505.03733},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.03733}, 
}

@misc{lu2025webgenagentenhancinginteractivewebsite,
      title={WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning}, 
      author={Zimu Lu and Houxing Ren and Yunqiao Yang and Ke Wang and Zhuofan Zong and Junting Pan and Mingjie Zhan and Hongsheng Li},
      year={2025},
      eprint={2509.22644},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2509.22644}, 
}