---
title: DeepSeek-R1-Distill-Qwen-7B-int4-ov
canonical_url: "https://www.modelscope.cn/models/zhaohb/DeepSeek-R1-Distill-Qwen-7B-int4-ov"
md_url: "https://www.modelscope.cn/models/zhaohb/DeepSeek-R1-Distill-Qwen-7B-int4-ov.md"
repository: zhaohb/DeepSeek-R1-Distill-Qwen-7B-int4-ov
last_updated: 2025-03-19
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
library_name:
  - openvino
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 908
stars: 0
---

# DeepSeek-R1-Distill-Qwen-7B-int4-ov

> DeepSeek-R1-Distill-Qwen-7B-int4-ov - zhaohb 在 ModelScope 开源的模型。Description This is deepseek-ai/DeepSeek-R1-Distill-Qwen-7B model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT4 by NNCF.

zhaohb/DeepSeek-R1-Distill-Qwen-7B-int4-ov 是 ModelScope 魔搭社区上的text-generation模型，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: zhaohb/DeepSeek-R1-Distill-Qwen-7B-int4-ov
- **Tasks**: text-generation
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 908
- **Stars**: 0
- **Last updated**: 2025-03-19

Source: https://www.modelscope.cn/models/zhaohb/DeepSeek-R1-Distill-Qwen-7B-int4-ov

---

### Description
This is deepseek-ai/DeepSeek-R1-Distill-Qwen-7B model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT4 by NNCF.

### Quantization Parameters
Weight compression was performed using nncf.compress_weights with the following parameters:

- mode: INT4_SYM
- group_size: 128
- ratio: 1.0