---
title: OpenSeek-Small-v1-SFT
canonical_url: "https://www.modelscope.cn/models/BAAI/OpenSeek-Small-v1-SFT"
md_url: "https://www.modelscope.cn/models/BAAI/OpenSeek-Small-v1-SFT.md"
repository: BAAI/OpenSeek-Small-v1-SFT
last_updated: 2025-09-08
license: open-mdw
model_type:
  - deepseek_v3
architectures:
  - DeepseekV3ForCausalLM
base_model:
  - BAAI/OpenSeek-Small-v1
base_model_relation: finetune
parameters: 1.6B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 189
stars: 0
---

# OpenSeek-Small-v1-SFT

> OpenSeek-Small-v1-SFT - BAAI 在 ModelScope 开源的模型。OpenSeek-Small-v1-SFT Documentation

BAAI/OpenSeek-Small-v1-SFT 是 ModelScope 魔搭社区上的 1.6B 参数机器学习模型，采用 open-mdw 许可，基于 BAAI/OpenSeek-Small-v1 构建，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: BAAI/OpenSeek-Small-v1-SFT
- **License**: open-mdw
- **Parameters**: 1.6B
- **Base model**: BAAI/OpenSeek-Small-v1
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 189
- **Stars**: 0
- **Last updated**: 2025-09-08

Source: https://www.modelscope.cn/models/BAAI/OpenSeek-Small-v1-SFT

---

# OpenSeek-Small-v1-SFT Documentation

## Overview
We adopt the  [Octothinker](https://natural-rugby-f7c.notion.site/OctoThinker-Revisiting-Mid-Training-In-the-Era-of-RL-Scaling-1d20b810e2d680c494a9f9dad0a90d53) to build strong reasoning foundations. Our model's training consists of two phases: a mid-training stable phase on 200 billion tokens from a mathematical corpus, followed by a 20 billion token decay phase. Subsequently, we fine-tune the model on the [Infinity-Instruct](https://huggingface.co/datasets/BAAI/Infinity-Instruct/tree/main/7M_core) dataset to achieve superior instruction-following capabilities. This model is open-sourced as a baseline for future experiments, such as enhancing the reasoning capabilities of small models through reinforcement learning. The model architecture is the same as the OpenSeek-Small-v1 model.

## Evaluation

|Metric | GSM8K | MATH-500 | Minerva Math | OlympiadBench | Avg. |
|:--- | :--- | :--- | :--- | :--- | :--- |
|Pass@1 | 20.698 | 13.100 | 3.470 | 2.741 | 10.002 |
|Pass@4 | 41.768 | 19.100 | 8.415 | 4.997 | 18.570 |
 |Pass@8 | 51.838 | 19.599 | 11.680 | 5.185 | 22.075 |

## License
[OpenMDW 1.0](https://github.com/OpenMDW/OpenMDW/blob/main/1.0/LICENSE.openmdw)