Kwai-Keye

5 models • 1 total models in database
Sort by:

Keye-VL-8B-Preview

NaNK
license:apache-2.0
52,500
82

Keye-VL-1_5-8B

--- language: - en library_name: transformers license: apache-2.0 pipeline_tag: video-text-to-text tags: - multimodal ---

NaNK
license:apache-2.0
46,057
63

Thyme-RL

[šŸ“– Home Page] [šŸ“– Github Repo] [šŸ“– Technique Report] [šŸ“Š Thyme SFT Model] [šŸ“Š Thyme RL Model] [šŸ“ SFT Data] [šŸ“ RL Data] šŸ”„ 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. We have provided the usage instructions, training code, and evaluation code in the GitHub repo. If you find Thyme useful in your research or applications, please cite our paper:

license:mit
1,528
12

Keye-VL-671B-A37B

NaNK
license:apache-2.0
45
18

Thyme-SFT

[šŸ“– Home Page] [šŸ“– Github Repo] [šŸ“– Technique Report] [šŸ“Š Thyme SFT Model] [šŸ“Š Thyme RL Model] [šŸ“ SFT Data] [šŸ“ RL Data] šŸ”„ 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. We have provided the usage instructions, training code, and evaluation code in the GitHub repo. If you find Thyme useful in your research or applications, please cite our paper:

NaNK
license:mit
43
6