---
title: SVPO_7B
canonical_url: "https://www.modelscope.cn/models/iic/SVPO_7B"
md_url: "https://www.modelscope.cn/models/iic/SVPO_7B.md"
repository: iic/SVPO_7B
last_updated: 2024-06-19
pipeline_tag: nli
tasks:
  - nli
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 6.9B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 68
stars: 0
---

# SVPO_7B

> SVPO_7B - iic 在 ModelScope 开源的模型。Step-level Value Preference Optimization for Mathematical Reasoning

iic/SVPO_7B 是 ModelScope 魔搭社区上的 6.9B 参数nli模型，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: iic/SVPO_7B
- **Tasks**: nli
- **Parameters**: 6.9B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 68
- **Stars**: 0
- **Last updated**: 2024-06-19

Source: https://www.modelscope.cn/models/iic/SVPO_7B

---

# Step-level Value Preference Optimization for Mathematical Reasoning

This is the official repository for paper [Step-level Value Preference Optimization for Mathematical Reasoning](https://arxiv.org/abs/2406.10858). It is extracted from our internal corporate codebase. As a result, there may be slight differences when reproducing the numbers reported in our paper, but they should be very close.


The implementation of SVPO is based on [AlphaMath](https://arxiv.org/abs/2405.03553), such as MCTS and Step-level beam search (SBS).
Therefore, we provide the [code](https://github.com/MARIO-Math-Reasoning/Super_MARIO) of step-level preference pairs construction in this repository to facilitate reproduction.


## Citation
SVPO
```
@misc{chen2024steplevel,
      title={Step-level Value Preference Optimization for Mathematical Reasoning}, 
      author={Guoxin Chen and Minpeng Liao and Chengxi Li and Kai Fan},
      year={2024},
      eprint={2406.10858},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
```

AlphaMATH
```
@misc{chen2024alphamath,
      title={AlphaMath Almost Zero: process Supervision without process}, 
      author={Guoxin Chen and Minpeng Liao and Chengxi Li and Kai Fan},
      year={2024},
      eprint={2405.03553},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
```