Demo (CN / Global) · GitHub · Free API · Usage · DSpark · Skill

MiniCPM-OCR 1.0 DSpark

This repository hosts the DSpark draft (speculative decoding) head for MiniCPM-OCR 1.0. It is a draft model, not a standalone OCR model — it must be paired with the matching main checkpoint.

DSpark speeds up decoding with a small draft model that proposes tokens the main model then verifies in one pass. With this head, MiniCPM-OCR 1.0 improves end-to-end processing efficiency by 55%; throughput reaches about 1.49× PaddleOCR-VL-1.6 and 3.62× MinerU2.5 Pro.

Specification

The output LM head and the Markov output rows are cropped to 114,688 tokens. The checkpoint keeps its d2t offset mapping and the full input vocabulary; local-to-target.json holds the corresponding absolute target token IDs.

Note on d2t: in this checkpoint the tensor is delta-encoded (target_id - draft_id). It must be converted to absolute IDs (d2t[i] + i) before use — the GGUF build already does this, and local-to-target.json is the ground truth to verify against.

Parsing pipeline

MiniCPM-OCR 1.0 parses full documents as a two-stage pipeline orchestrated by the minicpm-ocr SDK. The two stages use separate models, run in separate environments, and may run on different machines:

• Stage 1 — Layout detection (SDK environment). The PP-DocLayoutV3 layout model detects document regions — text, tables, formulas, charts, seals — and determines reading order; the SDK crops each region. It runs locally inside the SDK environment and requires PaddlePaddle / PaddleX.
• Stage 2 — Region recognition (inference service). The SDK sends each cropped region over HTTP to a MiniCPM-OCR 1.0 inference service — served by vLLM, SGLang, llama.cpp, or Ollama — with a prompt matching the region type, then assembles the recognized content into the final Markdown / JSON in reading order.

See the model guide for more on architecture, parsing workflow, deployment options, and benchmark breakdowns.

Usage with vLLM

vllm serve openbmb/MiniCPM-OCR-1.0 \
  --served-model-name MiniCPM-OCR \
  --trust-remote-code \
  --max-model-len 40960 \
  --max-num-batched-tokens 40960 \
  --max-num-seqs 1 \
  --trust-request-mm-kwargs \
  --mm-processor-kwargs '{"downsample_mode":"4x","max_slice_nums":9}' \
  --speculative-config '{"method":"dspark",
                         "model":"openbmb/MiniCPM-OCR-1.0-DSpark",
                         "num_speculative_tokens":15,
                         "enable_adaptive_verification":false}' \
  --default-chat-template-kwargs '{"enable_thinking":false}'

Selection and tuning: DSpark acceleration.

Related checkpoints

DSpark requires a matching main and draft model from the same release; do not pair this draft with a different main checkpoint.

FAQ

Installation, model downloads, GPU memory, input formats, and unexpected outputs: FAQ.

License

Model weights, code, and documentation are released under the Apache License 2.0.