---
title: gme-Qwen2-VL-2B-Instruct-fp16
canonical_url: "https://www.modelscope.cn/models/kristen123/gme-Qwen2-VL-2B-Instruct-fp16"
md_url: "https://www.modelscope.cn/models/kristen123/gme-Qwen2-VL-2B-Instruct-fp16.md"
repository: kristen123/gme-Qwen2-VL-2B-Instruct-fp16
chinese_name: gme-Qwen2-VL-2B-Instruct-fp16
last_updated: 2025-07-22
license: "Apache License 2.0"
pipeline_tag: multi-modal-embedding
tasks:
  - multi-modal-embedding
model_type:
  - qwen2_vl
architectures:
  - Qwen2VLForConditionalGeneration
parameters: 2.2B
tensor_type:
  - F16
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 579
stars: 0
---

# gme-Qwen2-VL-2B-Instruct-fp16

> gme-Qwen2-VL-2B-Instruct-fp16 - kristen123 在 ModelScope 开源的模型。这是一个用于多模态表征提取的模型，可以用来构建支持图文搜索的RAG

kristen123/gme-Qwen2-VL-2B-Instruct-fp16 是 ModelScope 魔搭社区上的 2.2B 参数multi-modal-embedding模型，采用 Apache License 2.0 许可，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: kristen123/gme-Qwen2-VL-2B-Instruct-fp16
- **License**: Apache License 2.0
- **Tasks**: multi-modal-embedding
- **Parameters**: 2.2B
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 579
- **Stars**: 0
- **Last updated**: 2025-07-22

Source: https://www.modelscope.cn/models/kristen123/gme-Qwen2-VL-2B-Instruct-fp16

---

这是一个用于多模态表征提取的模型，可以用来构建支持图文搜索的RAG

原模型在这里：https://modelscope.cn/models/iic/gme-Qwen2-VL-2B-Instruct/summary

这是量化的，由fp32量化到fp16，省显存用