---
title: Sky-T1-32B-Preview
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Sky-T1-32B-Preview"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Sky-T1-32B-Preview.md"
repository: AI-ModelScope/Sky-T1-32B-Preview
last_updated: 2025-01-14
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - Qwen/Qwen2.5-32B-Instruct
base_model_relation: finetune
parameters: 32.8B
tensor_type:
  - F16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 998
stars: 0
---

# Sky-T1-32B-Preview

> Sky-T1-32B-Preview - AI-ModelScope 在 ModelScope 开源的模型。This is a 32B reasoning model trained from Qwen2.5-32B-Instruct with 17K data. The performance is on par with o1-preview model on both math and coding. Please see our blog post for more details.

AI-ModelScope/Sky-T1-32B-Preview 是 ModelScope 魔搭社区上的 32.8B 参数text-generation模型，采用 apache-2.0 许可，基于 Qwen/Qwen2.5-32B-Instruct 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: AI-ModelScope/Sky-T1-32B-Preview
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 32.8B
- **Base model**: Qwen/Qwen2.5-32B-Instruct
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 998
- **Stars**: 0
- **Last updated**: 2025-01-14

Source: https://www.modelscope.cn/models/AI-ModelScope/Sky-T1-32B-Preview

---

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

This is a 32B reasoning model trained from Qwen2.5-32B-Instruct with 17K data. The performance is on par with o1-preview model on both math and coding.
Please see our [blog post](https://novasky-ai.github.io/posts/sky-t1/) for more details.

- **Developed by:** NovaSky Team from Sky Computing Lab at UC Berkeley.

## Training Details

### Training Data

17K verified correct responses from Qwen/QwQ-32B-Preview on coding, math. In addition, we add the science portion from the [Still-2 paper](https://arxiv.org/pdf/2412.09413).

### Training Procedure
We perform supervised fine tuning on the data, with a batch size of 96.

#### Speeds

We use Llama-Factory for training. On 8 H100, the training takes 19 hours with DeepSpeed Zero-3 Offload.


## Evaluation
|               | Sky-T1-32B-Preview | Qwen-2.5-32B-Instruct | QwQ   | o1-preview |
|-----------------------|---------------------|--------|-------|------------|
| Math500              | 82.4                    | 76.2    | 85.4 | 81.4       |
| AIME2024             | 43.3                    | 16.7    | 50.0  | 40.0       |
| LiveCodeBench-Easy   | 86.3                    | 84.6   | 90.7  | 92.9       |
| LiveCodeBench-Medium | 56.8                    | 40.8   | 56.3  | 54.9       |
| LiveCodeBench-Hard   | 17.9                    | 9.8   | 17.1  | 16.3       |
| GPQA-Diamond         | 56.8                    | 45.5   | 52.5  | 75.2       |

## Acknowledgement
We would like to thanks the compute resources from [Lambda Lab](https://lambdalabs.com/service/gpu-cloud?srsltid=AfmBOop5FnmEFTkavVtdZDsLWvHWNg6peXtat-OXJ9MW5GMNsk756PE5) and [AnyScale](https://www.anyscale.com/). We would like to thanks the academic feedback and support from the [Still-2 Team](https://arxiv.org/pdf/2412.09413), and [Junyang Lin](https://justinlin610.github.io/) from the [Qwen Team](https://qwenlm.github.io/). 

## Citation 
Please considering citing our blog post if you found it useful for your research. Thank you!

```bibtex
@misc{sky_t1_2025,
  author       = {NovaSky Team},
  title        = {Sky-T1: Fully open-source reasoning model with o1-preview performance in $450 budget},
  howpublished = {https://novasky-ai.github.io/posts/sky-t1},
  note         = {Accessed: 2025-01-09},
  year         = {2025}
}