Feature Extraction
Transformers
Safetensors
modernbert
html
document-embedding
text-embeddings-inference
Instructions to use Seznam/html-lm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Seznam/html-lm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Seznam/html-lm")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Seznam/html-lm") model = AutoModel.from_pretrained("Seznam/html-lm", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 626 Bytes
f2a3229 | 1 | <html><head><title>Nested HTML Example</title></head><body><nav><a>Home</a><a>About</a><a>Services</a><a>Contact</a></nav><div><h1>Simple Page</h1><main><div><h2>First Section</h2><p>Some example content inside the page.</p><p>This text is inside a deeper nested div.</p></div><div><h2>Second Section</h2><span>Text at a deeper level</span><nav><a>One</a><a>Two</a><a>Three</a></nav></div><div><h3>Nested Card</h3><div><p>Another nested text node.</p><span>Even deeper text</span></div></div></main><p>Footer information</p></div><p>This is text near the bottom of the DOM tree.</p><p>Text at the bottom node</p></body></html> |