---
title: Qwen2.5-14B-Instruct-w8a8-MindIE
canonical_url: "https://www.modelscope.cn/models/aleoyang/Qwen2.5-14B-Instruct-w8a8-MindIE"
md_url: "https://www.modelscope.cn/models/aleoyang/Qwen2.5-14B-Instruct-w8a8-MindIE.md"
repository: aleoyang/Qwen2.5-14B-Instruct-w8a8-MindIE
last_updated: 2025-05-08
license: "Apache License 2.0"
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - Qwen/Qwen2.5-14B-Instruct
base_model_relation: quantized
parameters: 14.8B
tensor_type:
  - I64
  - F16
  - I32
  - I8
library_name:
  - safetensors
  - other
frameworks:
  - other
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 12716
stars: 0
tags:
  - MindIE
  - "昇腾"
---

# Qwen2.5-14B-Instruct-w8a8-MindIE

> Qwen2.5-14B-Instruct-w8a8-MindIE - aleoyang 在 ModelScope 开源的模型。为华为NPU量化，MindIE使用。

aleoyang/Qwen2.5-14B-Instruct-w8a8-MindIE 是 ModelScope 魔搭社区上的 14.8B 参数text-generation模型，采用 Apache License 2.0 许可，基于 Qwen/Qwen2.5-14B-Instruct 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: aleoyang/Qwen2.5-14B-Instruct-w8a8-MindIE
- **License**: Apache License 2.0
- **Tasks**: text-generation
- **Parameters**: 14.8B
- **Base model**: Qwen/Qwen2.5-14B-Instruct
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: MindIE, 昇腾
- **Downloads**: 12716
- **Stars**: 0
- **Last updated**: 2025-05-08

Source: https://www.modelscope.cn/models/aleoyang/Qwen2.5-14B-Instruct-w8a8-MindIE

---

### 模型在华为910B3NPU的MindIE框架下进行w8a8量化。
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型

SDK下载
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('aleoyang/Qwen2.5-14B-Instruct-w8a8-MindIE')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/aleoyang/Qwen2.5-14B-Instruct-w8a8-MindIE.git
```