Instructions to use openbmb/MiniCPM-OCR-1.0-DSpark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM-OCR-1.0-DSpark with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="openbmb/MiniCPM-OCR-1.0-DSpark")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("openbmb/MiniCPM-OCR-1.0-DSpark")
model = AutoModel.from_pretrained("openbmb/MiniCPM-OCR-1.0-DSpark", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM-OCR-1.0-DSpark with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM-OCR-1.0-DSpark"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM-OCR-1.0-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM-OCR-1.0-DSpark

SGLang

How to use openbmb/MiniCPM-OCR-1.0-DSpark with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "openbmb/MiniCPM-OCR-1.0-DSpark" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM-OCR-1.0-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "openbmb/MiniCPM-OCR-1.0-DSpark" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM-OCR-1.0-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openbmb/MiniCPM-OCR-1.0-DSpark with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-OCR-1.0-DSpark
```

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

Property	Value
Target model	MiniCPM-OCR 1.0 (1.3B)
Draft parameters	296,837,889
Draft layers	5
Draft tokens per forward pass	15
Target hidden-state layers	`[3, 7, 11, 15, 19]`
Checkpoint precision	BF16
Input vocabulary	248,100
Draft output vocabulary	114,688

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.

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.

Files

File	Notes
`model.safetensors`	64 tensors — 5 draft layers, `fc` projector, `lm_head`, Markov heads, confidence head, `d2t`
`config.json`	`architectures: ["Qwen3DSparkModel"]`, `dflash_config` with target layer ids and Markov rank
`local-to-target.json`	114,688 absolute target token IDs, the reference for `d2t`
`export-audit.json`	export-time audit: weight/mapping hashes and vocabulary coverage

Related checkpoints

Format	Hugging Face	ModelScope
BF16 (original)	🤗	ModelScope
GGUF (llama.cpp)	🤗	ModelScope
AWQ W4A16	🤗	ModelScope
GPTQ W4A16	🤗	ModelScope
DSpark draft (BF16) (this repo)	🤗	ModelScope
DSpark draft (GGUF)	🤗	ModelScope

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.

Downloads last month: 888

Safetensors

Model size

0.3B params

Tensor type

I64

BF16

Model tree for openbmb/MiniCPM-OCR-1.0-DSpark

Base model

openbmb/MiniCPM-V-4.6

Finetuned

openbmb/MiniCPM-OCR-1.0

Finetuned

(5)

this model

Collection including openbmb/MiniCPM-OCR-1.0-DSpark

MiniCPM-OCR

Collection

Fast, accurate OCR with correctness assessment. • 10 items • Updated 4 days ago • 17