Gramscii-IT/DeepSeek-OCR-2-GGUF

DeepSeek-OCR-2 for SDG

DeepSeek-OCR-2 Q8_0 language weights and BF16 vision projector, distributed for Gramscii SDG local document reading. Both artifacts are required. Inference runs locally; documents are not uploaded to Hugging Face.

Original model: deepseek-ai/DeepSeek-OCR-2, Apache 2.0. GGUF conversion: sabafallah/DeepSeek-OCR-2-GGUF. These files are byte-identical to that pinned conversion; Gramscii does not claim authorship of the model or conversion.

Use llama.cpp with DeepSeek-OCR-2 support and the deepseek-ocr chat template, Jinja disabled, flash attention disabled. SDG owns download verification, process lifecycle and task-specific prompts. Its model manifest pins this repository's immutable revision and artifact checksums.

OCR text and coordinates require review. This model does not guarantee pixel-identical PDF reconstruction or correct identification of editable form fields.