TAID-VLM-2B

🐟 TAID-VLM-2B

🤗 Models | 📚 Paper | 📝 Blog | 🐦 Twitter

TAID-VLM-2B is a vision-language model created through TAID (Temporally Adaptive Interpolated Distillation), our new knowledge distillation method. We used InternVL2-8B as the teacher model and InternVL2-2B as the student model.

Model Details

• Developed by: Sakana AI
• Model type: Autoregressive Vision-Language Model
• Language(s): English
• License: MIT License
• Paper: https://arxiv.org/abs/2501.16937
• Blog: https://sakana.ai/taid/

Uses

This model is provided for research and development purposes only and should be considered as an experimental prototype. It is not intended for commercial use or deployment in mission-critical environments. Use of this model is at the user's own risk, and its performance and outcomes are not guaranteed. Sakana AI shall not be liable for any direct, indirect, special, incidental, or consequential damages, or any loss arising from the use of this model, regardless of the results obtained. Users must fully understand the risks associated with the use of this model and use it at their own discretion.

Acknowledgement

We would like to thank the developers of the source models for their contributions and for making their work available.

This model is based on results obtained from a project, JPNP20017, subsidized by the New Energy and Industrial Technology Development Organization (NEDO).

Citation

@misc{sakana2025taid,
      title         = {TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models}, 
      author.       = {Makoto Shing and Kou Misaki and Han Bao and Sho Yokoi and Takuya Akiba},
      year          = {2025},
      eprint        = {2501.16937},
      archivePrefix = {arXiv},
      primaryClass  = {cs.LG},
      url           = {https://arxiv.org/abs/2501.16937}
}