← Latest products

Compress vision-language and unimodal AI models by structured pruning

[ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers.

Open source

103 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Komposer

    komposer.xyz

    AI image editor where the LLM writes the prompts

    Hacker News12 pts

  2. A collection of tutorials and notebooks explaining transformer models in deep learning.

    Hacker News14 pts

  3. TRiP

    github.com

    a complete transformer engine in C built from scratch just by me

    Hacker News38 pts

  4. PyTorch LLMs with less code duplication

    Hacker News10 pts

  5. Pruna AI

    news.ycombinator.com

    Inference Optimization Engine

    Hacker News6 pts