---
title: MiniCPM-V-4.7-1B-DSpark
canonical_url: "https://www.modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-1B-DSpark"
md_url: "https://www.modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-1B-DSpark.md"
repository: OpenBMB/MiniCPM-V-4.7-1B-DSpark
last_updated: 2026-10-12
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3
architectures:
  - Qwen3DSparkModel
parameters: 213.5M
tensor_type:
  - BF16
library_name:
  - safetensors
language:
  - en
  - zh
downloads: 12
stars: 0
tags:
  - minicpmv
  - minicpmv4.7
  - text-generation
  - vision-understanding
  - tool-calling
  - on-device
  - edge-ai
---

# MiniCPM-V-4.7-1B-DSpark

> MiniCPM-V-4.7-1B-DSpark - OpenBMB 在 ModelScope 开源的模型。MiniCPM-V-4.7-1B-DSpark

OpenBMB/MiniCPM-V-4.7-1B-DSpark 是 ModelScope 魔搭社区上的 213.5M 参数text-generation模型，采用 apache-2.0 许可。

- **Repository**: OpenBMB/MiniCPM-V-4.7-1B-DSpark
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 213.5M
- **Tags**: minicpmv, minicpmv4.7, text-generation, vision-understanding, tool-calling, on-device, edge-ai
- **Downloads**: 12
- **Stars**: 0
- **Last updated**: 2026-10-12

Source: https://www.modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-1B-DSpark

---

# MiniCPM-V-4.7-1B-DSpark

`MiniCPM-V-4.7-1B-DSpark` is a [DSpark](https://arxiv.org/abs/2607.05147) draft checkpoint trained for exact pairing with [MiniCPM-V-4.7-1B](https://huggingface.co/openbmb/MiniCPM-V-4.7-1B) and its tokenizer.


## Model Specification

| Property | Value |
|---|---|
| Target model | [MiniCPM-V-4.7-1B](https://huggingface.co/openbmb/MiniCPM-V-4.7-1B) |
| Draft layers | 5 |
| Draft parameters | 213,547,777 |
| Draft tokens per forward pass | 15 |
| Target hidden-state layers | `[3, 7, 11, 15, 19]` |
| Checkpoint precision | BF16 |

## Training Recipe

Training responses were generated by [MiniCPM-V-4.7-1B](https://huggingface.co/openbmb/MiniCPM-V-4.7-1B) from a mixture of Vision & Text prompts.

| Setting | Value |
|---|---|
| Training sequences | 2M |
| Epochs | 6 |
| Optimizer | AdamW |
| Objective | CE + L1 + confidence loss |

## Evaluation

Acceptance length is defined as the total number of completion tokens divided by the total number of speculative verification steps. Evaluation uses natural EOS termination and `max_new_tokens=8192`.


| **Domain**            | **Accept Length** | 
| --------------------- | ----------------- |
| **Vision**            |                   |
| MMMU                  | 3.452             |
| MathVista             | 4.333             |
| CharXiv_reasoning_val | 4.452             |
| OCRBench              | 4.752             |
| **Text**              |                   |
| Math                  | 5.891             |
| Code                  | 5.347             |
| General               | 3.370             |



## Usage with vLLM

```bash
vllm serve \
  --model openbmb/MiniCPM-V-4.7-1B \
  --served-model-name MiniCPM-V-4.7-1B \
  --max-model-len 40960 \
  --max-num-batched-tokens 40960 \
  --max-num-seqs 1 \
  --attention-backend FLASH_ATTN \
  --mm-encoder-attn-backend FLASH_ATTN \
  --mm-processor-kwargs '{"downsample_mode":"4x"}' \
  --trust-request-mm-kwargs \
  --speculative-config '{"method":"dspark","model":"openbmb/MiniCPM-V-4.7-1B-DSpark","num_speculative_tokens":15,"enable_adaptive_verification":false}' \
  --default-chat-template-kwargs '{"enable_thinking":false}' \
```


## Limitations and Disclaimer

This model has no autonomous intent or legal personhood; its outputs are text generated from statistical patterns and may be inaccurate, biased, or offensive, and may be manipulated by carefully crafted prompts ("jailbreaks") into producing unintended content. Its responses on sensitive topics such as politics, health, finance, and law are not reviewed by experts and should not be treated as professional advice.

This model is provided "**AS IS**", without warranty of any kind, express or implied, and the developers are not liable for any damages arising from its use. Users must employ the model only for lawful, compliant, and ethical purposes, configure their own safeguards, and label AI-generated content where required; deliberate jailbreaking, injection attacks, or inducing harmful output is prohibited, and any such testing is at the user's own risk.