---
title: HSA-DPO
canonical_url: "https://www.modelscope.cn/models/xiaowenyi/HSA-DPO"
md_url: "https://www.modelscope.cn/models/xiaowenyi/HSA-DPO.md"
repository: xiaowenyi/HSA-DPO
last_updated: 2025-12-16
license: "Apache License 2.0"
model_type:
  - llava
architectures:
  - LlavaLlamaForCausalLM
inference_backends:
  - "deploy_task vlm"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
downloads: 35
stars: 0
---

# HSA-DPO

> HSA-DPO - xiaowenyi 在 ModelScope 开源的模型。LoRA weight of Llava-v1.5-13B in HSA-DPO.

xiaowenyi/HSA-DPO 是 ModelScope 魔搭社区上的机器学习模型，采用 Apache License 2.0 许可，可用 deploy_task vlm、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: xiaowenyi/HSA-DPO
- **License**: Apache License 2.0
- **Inference backends**: deploy_task vlm, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2
- **Downloads**: 35
- **Stars**: 0
- **Last updated**: 2025-12-16

Source: https://www.modelscope.cn/models/xiaowenyi/HSA-DPO

---

LoRA weight of Llava-v1.5-13B in HSA-DPO.


Please follow the Instruction in Github repository, repo: https://github.com/Mr-Loevan/HSA-DPO