Instructions to use Ambition0303/Qwen-HTML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ambition0303/Qwen-HTML with Transformers:

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

pipe = pipeline("text-generation", model="Ambition0303/Qwen-HTML")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ambition0303/Qwen-HTML")
model = AutoModelForCausalLM.from_pretrained("Ambition0303/Qwen-HTML", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ambition0303/Qwen-HTML with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ambition0303/Qwen-HTML"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ambition0303/Qwen-HTML",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ambition0303/Qwen-HTML

SGLang

How to use Ambition0303/Qwen-HTML 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 "Ambition0303/Qwen-HTML" \
    --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": "Ambition0303/Qwen-HTML",
		"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 "Ambition0303/Qwen-HTML" \
        --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": "Ambition0303/Qwen-HTML",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ambition0303/Qwen-HTML with Docker Model Runner:
```
docker model run hf.co/Ambition0303/Qwen-HTML
```

Qwen-HTML 4B

Qwen-HTML is a lightweight HTML-specialized model for Co-Scraper, a query-aware web data extraction framework. It is initialized from Qwen/Qwen3-4B and trained for two complementary tasks:

Node identification: select the DOM nodes most likely to contain query-relevant records and attributes.
Scraper synthesis: generate reusable Python extraction code over the pruned HTML.

The model is designed to reduce the cost and failure rate of web information extraction by working with compact, query-aware DOM views instead of full raw pages.

Model description

Base model: Qwen3-4B
Architecture: Qwen3ForCausalLM
Precision: bfloat16
Context length: 131,072 tokens

Intended use

Deploy the model with vLLM as an OpenAI-compatible service:

pip install vllm

vllm serve Ambition0303/Qwen-HTML \
  --served-model-name qwen-html \
  --dtype bfloat16 \
  --tensor-parallel-size 1 \
  --max-model-len 131072 \
  --port 8000

Then use the endpoint with the Co-Scraper inference pipeline:

export OPENAI_BASE_URL="http://localhost:8000/v1"
export OPENAI_API_KEY="not-required"

coscraper \
  "Extract the camera model and price." \
  schema.json \
  seed_1.html seed_2.html seed_3.html \
  --model qwen-html

Set --tensor-parallel-size to the number of GPUs used for tensor parallelism. If GPU memory is insufficient for the full 131,072-token context, reduce --max-model-len according to your deployment budget.

Evaluation

Results from the Co-Scraper paper. Higher is better except Unex.f.

Dataset	Precision	Recall	F1	Cor_p	Cor_f	Unex._f
SWDE	95.93	96.24	96.00	85.87	95.51	3.19
LiveWeb-IE	92.29	92.68	92.40	82.00	91.28	6.08

Metric definitions:

F1 ： field-level extraction quality.
Cor_p ： page-level perfect extraction rate.
Cor_f ： field-level cross-page reuse success rate.
Unex._f ： fraction of fields with unexecutable or invalid output.

Limitations

Generated scrapers should still be reviewed before being executed on untrusted pages. Model performance can vary with HTML quality, site structure, and query clarity.

Citation

If you use this model, please cite the Co-Scraper work:

@misc{coscraper2026,
  title={Co-Scraper: Query-Aware DOM Pruning and Reusable Scraper Synthesis for Lightweight Web Data Extraction},
  author={Wang, Shoupeng and Qiu, Jiantao and Zhang, Wuyang and He, Conghui},
  year={2026},
  url={https://arxiv.org/abs/2606.14821}