Add SuperCompress to Pre-trained Models and Inference

[arjunkshah]

Add SuperCompress to the Pre-trained Models and Inference section.

Learned prompt compression that reduces LLM token costs by ~65%. ~5K-param CPU policy, open-source (MIT).

• GitHub: https://github.com/arjunkshah/supercompress
• PyPI: pip install supercompress

[JinyangWang27]

@arjunkshah Thanks for your submission. However, this project does not meet our acceptance criteria:

Repository age: The repository was created 3 weeks ago. We require a minimum of 3 months (or 6 months for Hidden Gem submissions) to ensure project stability.

GitHub stars: 3 stars (minimum 100 required, or strong justification for Hidden Gem).

Please see our CONTRIBUTING.md for full requirements. You're welcome to resubmit once the project has matured and gained community traction.