oklenAI/udm_doc_extract_qwen3.5_2B

Long-page fix: continued training on 22,256 pairs from pages the 20k-char cap had dropped

Update model card for long-page-fixed revision

Disclose measured length limitation: no training page exceeds 20,000 chars

Qwen3.5-2B distilled for math-content extraction (197,269 GPT-5.6 pairs)

initial commit