---
title: Docopilot-2B
canonical_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/Docopilot-2B"
md_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/Docopilot-2B.md"
repository: Shanghai_AI_Laboratory/Docopilot-2B
last_updated: 2025-07-20
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - internvl_chat
architectures:
  - InternVLChatModel
parameters: 2.2B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 218
stars: 0
---

# Docopilot-2B

> Docopilot-2B - Shanghai_AI_Laboratory 在 ModelScope 开源的模型。This model is in the paper Docopilot: Improving Multimodal Models for Document-Level Understanding.

Shanghai_AI_Laboratory/Docopilot-2B 是 ModelScope 魔搭社区上的 2.2B 参数image-text-to-text模型，采用 mit 许可，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: Shanghai_AI_Laboratory/Docopilot-2B
- **License**: mit
- **Tasks**: image-text-to-text
- **Parameters**: 2.2B
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 218
- **Stars**: 0
- **Last updated**: 2025-07-20

Source: https://www.modelscope.cn/models/Shanghai_AI_Laboratory/Docopilot-2B

---

This model is in the paper [Docopilot: Improving Multimodal Models for Document-Level Understanding](https://openaccess.thecvf.com/content/CVPR2025/html/Duan_Docopilot_Improving_Multimodal_Models_for_Document-Level_Understanding_CVPR_2025_paper.html).

Please refer to https://github.com/OpenGVLab/Docopilot for details.