inference-net/Schematron-8B

inference-net/Schematron-8B is an 8 billion parameter model from the Schematron series, developed by Inference.net. This model is purpose-trained for long-context extraction, specializing in converting noisy HTML into clean, typed JSON that conforms to a custom schema. With a 32K token context window, it excels at web scraping, data ingestion, and transforming arbitrary web pages into structured records, offering 100% schema-conformant JSON outputs.