jinaai/reader-lm-0.5b

Jina AI's reader-lm-0.5b is a 0.5 billion parameter language model specifically designed for converting HTML content into Markdown. This model, part of the Jina Reader-LM series, features a substantial 32768 token context length, enabling it to process extensive web pages. It is trained on a curated dataset of HTML and corresponding Markdown content, making it highly effective for content conversion tasks. Its primary application is to streamline the transformation of web content into a more readable and portable format.

Warm
Public
0.5B
BF16
32768
License: cc-by-nc-4.0
Hugging Face