commit c6c6bbb2d4c15529a1d2fa1e0ab95c5cc9f3400e Author: ModelHub XC Date: Thu May 28 18:08:39 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: luzimu/WebGen-LM-14B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..828b6da --- /dev/null +++ b/README.md @@ -0,0 +1,123 @@ +--- +base_model: +- Qwen/Qwen2.5-Coder-7B-Instruct +datasets: +- luzimu/WebGen-Bench +language: +- en +library_name: transformers +license: mit +metrics: +- accuracy +pipeline_tag: text-generation +tags: +- code-generation +--- + +# WebGen-LM + +WebGen-LM is a code language model specifically trained for generating interactive and functional websites from scratch. It is trained using the Bolt.diy trajectories generated from a subset of the training set of WebGen-Bench (🤗 [luzimu/WebGen-Bench](https://huggingface.co/datasets/luzimu/WebGen-Bench)). It has been introduced in the paper [WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch](https://arxiv.org/abs/2505.03733). + +The training data and code can be found at [WebGen-Bench (Github)](https://github.com/mnluzimu/WebGen-Bench). + +The WebGen-LM family of models are as follows: + +|Models | HF Links | +|---|---| +|WebGen-LM-7B | 🤗 [luzimu/WebGen-LM-7B](https://huggingface.co/luzimu/WebGen-LM-7B) | +|WebGen-LM-14B | 🤗 [luzimu/WebGen-LM-14B](https://huggingface.co/luzimu/WebGen-LM-14B) | +|WebGen-LM-32B | 🤗 [luzimu/WebGen-LM-32B](https://huggingface.co/luzimu/WebGen-LM-32B) | + +## Performance on WebGen-Bench + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b0bfef2f2f9c345b87e673/ADt1JdvKw-IZ_xnS17adL.png) + +## Usage + +You can use `WebGen-LM` with the `transformers` library to generate website code. + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model_id = "luzimu/WebGen-LM-32B" # You can also use WebGen-LM-7B or WebGen-LM-14B + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto" +) + +# Example for website generation +prompt = """Generate the complete HTML, CSS, and JavaScript code for a responsive website. +The website should be a simple landing page for a coffee shop. +It needs: +1. A navigation bar at the top with "Home", "Menu", "About Us", and "Contact" links. +2. A hero section with a background image, a title "Brewing Perfection", and a call-to-action button "View Our Menu". +3. A menu section displaying at least 3 coffee items with their names and prices. +4. An "About Us" section with a brief description of the coffee shop. +5. A "Contact" section with an address, phone number, and a simple contact form (Name, Email, Message, Submit button). +6. Basic responsive design for mobile views. +""" + +messages = [ + {"role": "user", "content": prompt} +] + +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True +) + +model_inputs = tokenizer([text], return_tensors="pt").to(model.device) + +generated_ids = model.generate( + model_inputs.input_ids, + max_new_tokens=2048, # Adjust as needed for full website code + do_sample=True, + temperature=0.7, + top_p=0.9, + repetition_penalty=1.05, +) + +# Decode the generated output, skipping special tokens +response = tokenizer.batch_decode(generated_ids[0], skip_special_tokens=True)[0] +# The response will contain the full conversation history including the input prompt. +# To get only the newly generated text, you might need to slice it or use the appropriate +# tokenizer behavior based on how apply_chat_template adds prompt. +# For simplicity, if the model just appends to the prompt, direct decode might suffice. +# A more robust approach might be: +# generated_text_only = tokenizer.decode(generated_ids[0][len(model_inputs.input_ids[0]):], skip_special_tokens=True) +print(response) + +# You might need to parse the output to separate HTML, CSS, and JS if the model outputs a combined file. +# For example, look for specific markers like ,