---
title: Thyme-RL
canonical_url: "https://www.modelscope.ai/models/Kwai-Keye/Thyme-RL"
md_url: "https://www.modelscope.ai/models/Kwai-Keye/Thyme-RL.md"
repository: Kwai-Keye/Thyme-RL
last_updated: 2026-05-29
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen2_5_vl
architectures:
  - Qwen2_5_VLForConditionalGeneration
base_model:
  - Qwen/Qwen2.5-VL-7B-Instruct
base_model_relation: finetune
parameters: 8.3B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 163
stars: 0
---

# Thyme-RL

> Thyme-RL - An open-source model by Kwai-Keye on ModelScope. [📖 Home Page] [📖 Github Repo] [📖 Technique Report]

Kwai-Keye/Thyme-RL is a 8.3B-parameter image-text-to-text model on ModelScope. licensed under mit. derived from Qwen/Qwen2.5-VL-7B-Instruct.

- **Repository**: Kwai-Keye/Thyme-RL
- **License**: mit
- **Tasks**: image-text-to-text
- **Parameters**: 8.3B
- **Base model**: Qwen/Qwen2.5-VL-7B-Instruct
- **Downloads**: 163
- **Stars**: 0
- **Last updated**: 2026-05-29

Source: https://www.modelscope.ai/models/Kwai-Keye/Thyme-RL

---

<div align="center">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/685ba798484e3233f5ff6f11/dxBp6TmwqwNuBuJR9gfQC.png" width="40%" alt="Thyme Logo">
</div>

<font size=4><div align='center' >  
[[📖 Home Page](https://thyme-vl.github.io/)] 
[[📖 Github Repo](https://github.com/yfzhang114/Thyme)] 
[[📖 Technique Report](https://arxiv.org/abs/2508.11630)] 

[[📊 Thyme SFT Model](https://huggingface.co/Kwai-Keye/Thyme-SFT)] 
[[📊 Thyme RL Model](https://huggingface.co/Kwai-Keye/Thyme-RL)] 
[[📝 SFT Data](https://huggingface.co/datasets/Kwai-Keye/Thyme-SFT)] 
[[📝 RL Data](https://huggingface.co/datasets/Kwai-Keye/Thyme-RL)] 
</div></font>

## 🔥 News
* **`2025.08.15`** 🌟 We are excited to introduce **Thyme: Think Beyond Images**. Thyme transcends traditional ``thinking with images'' paradigms by autonomously generating and executing diverse image processing and computational operations through executable code, significantly enhancing performance on high-resolution perception and complex reasoning tasks. Leveraging a novel two-stage training strategy that combines supervised fine-tuning with reinforcement learning and empowered by the innovative GRPO-ATS algorithm, Thyme achieves a sophisticated balance between reasoning exploration and code execution precision.

<div align="center">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/685ba798484e3233f5ff6f11/c_D7uX3RT1WUANDRB70ZC.png" width="100%" alt="Thyme Logo">
</div>

We have provided the usage instructions, training code, and evaluation code in the [GitHub repo](https://github.com/yfzhang114/Thyme).

## Citation

If you find Thyme useful in your research or applications, please cite our paper:

```bibtex
@article{zhang2025thyme,
  title={Thyme: Think Beyond Images},
  author={Kwai Keye},
  journal={arXiv preprint},
  year={2025}
}
```