---
title: PIIP-LLaVA-Plus_ConvNeXt-L_CLIP-L_1024-336_7B
canonical_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/PIIP-LLaVA-Plus_ConvNeXt-L_CLIP-L_1024-336_7B"
md_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/PIIP-LLaVA-Plus_ConvNeXt-L_CLIP-L_1024-336_7B.md"
repository: Shanghai_AI_Laboratory/PIIP-LLaVA-Plus_ConvNeXt-L_CLIP-L_1024-336_7B
last_updated: 2025-04-20
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - llava_llama
architectures:
  - LlavaLlamaForCausalLM
base_model:
  - lmsys/vicuna-7b-v1.5
base_model_relation: merge
parameters: 7.3B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task vlm"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
downloads: 470
stars: 0
tags:
  - llava
  - vision
  - ocr
  - custom_code
---

# PIIP-LLaVA-Plus_ConvNeXt-L_CLIP-L_1024-336_7B

> PIIP-LLaVA-Plus_ConvNeXt-L_CLIP-L_1024-336_7B - Shanghai_AI_Laboratory 在 ModelScope 开源的模型。This repository contains the PIIP-LLaVA-PlusConvNeXt-LCLIP-L1024-3367B model, based on vicuna-7b-v1.5.

Shanghai_AI_Laboratory/PIIP-LLaVA-Plus_ConvNeXt-L_CLIP-L_1024-336_7B 是 ModelScope 魔搭社区上的 7.3B 参数image-text-to-text模型，采用 mit 许可，基于 lmsys/vicuna-7b-v1.5 构建，可用 deploy_task vlm、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: Shanghai_AI_Laboratory/PIIP-LLaVA-Plus_ConvNeXt-L_CLIP-L_1024-336_7B
- **License**: mit
- **Tasks**: image-text-to-text
- **Parameters**: 7.3B
- **Base model**: lmsys/vicuna-7b-v1.5
- **Inference backends**: deploy_task vlm, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2
- **Tags**: llava, vision, ocr, custom_code
- **Downloads**: 470
- **Stars**: 0
- **Last updated**: 2025-04-20

Source: https://www.modelscope.cn/models/Shanghai_AI_Laboratory/PIIP-LLaVA-Plus_ConvNeXt-L_CLIP-L_1024-336_7B

---

This repository contains the PIIP-LLaVA-Plus_ConvNeXt-L_CLIP-L_1024-336_7B model, based on vicuna-7b-v1.5.

Please refer to our [**paper**](https://huggingface.co/papers/2501.07783) and [**GitHub repository**](https://github.com/OpenGVLab/PIIP/tree/main/llava) for introduction and usage.



## Citation

If you find this project useful in your research, please consider citing:

```BibTeX
@article{piip,
  title={Parameter-Inverted Image Pyramid Networks},
  author={Zhu, Xizhou and Yang, Xue and Wang, Zhaokai and Li, Hao and Dou, Wenhan and Ge, Junqi and Lu, Lewei and Qiao, Yu and Dai, Jifeng},
  journal={arXiv preprint arXiv:2406.04330},
  year={2024}
}

@article{piip_v2,
  title={Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding},
  author={Wang, Zhaokai and Zhu, Xizhou and Yang, Xue and Luo, Gen and Li, Hao and Tian, Changyao and Dou, Wenhan and Ge, Junqi and Lu, Lewei and Qiao, Yu and Dai, Jifeng},
  journal={arXiv preprint arXiv:2501.07783},
  year={2025}
}
```