ReaderLM 0.5B
ReaderLM 0.5B is a trained HTML-to-Markdown converter. Jina built it from paired HTML and Markdown examples, with a stated 256K context. It is part of the first ReaderLM release rather than a general conversation model.
How the model works
The 0.5B size targets a smaller local inference footprint. The documented prompt is raw HTML and needs no instruction prefix. Its output is a text representation of the page content. Fetching URLs and executing browser scripts belong to the application that supplies that HTML, not to this model.ReaderLM 0.5B model details
Use and access
Weights remain available under CC BY-NC 4.0, alongside documented cloud marketplace packages. The provider now points users toward ReaderLM v2, but that does not remove this identifiable older checkpoint. The two first-generation sizes have distinct weights and are listed separately.ReaderLM 0.5B model detailsReaderLM 0.5B technical overview
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | |
| Access | Downloadable |
| Model identifiers | reader-lm-0.5bjinaai/reader-lm-0.5b |
| Context window | 256,000 tokens Exact max_position_embeddings value in the published configuration; the model card abbreviates this as 256K. Input and generated output share the context. reader-lm-0.5b published model configuration |
| Parameters | 0.5 billionReaderLM 0.5B model details |
| Weight license | CC BY-NC 4.0ReaderLM 0.5B model details |
Related models
- ReaderLM v2
Jina AI · ReaderLM
A small language model that turns HTML into Markdown or schema-based JSON.
Launch date API · Downloadable - ReaderLM 1.5B
Jina AI · ReaderLM
The larger first-generation ReaderLM model for HTML-to-Markdown conversion.
Launch date Downloadable