PZ's picture

PZ PRO

philipp-zettl

AI & ML interests

NLP/CV/Multimodal learning

Recent Activity

liked a dataset about 2 hours ago
SakanaAI/AI-CUDA-Engineer-Archive
new activity 2 days ago
philipp-zettl/chessPT:Any results?
liked a model 4 days ago
perplexity-ai/r1-1776
View all activity

Organizations

Blog-explorers's profile picture easybits's profile picture

philipp-zettl's activity

New activity in philipp-zettl/chessPT 2 days ago

Any results?

3
#2 opened 18 days ago by
AlvaroMros
New activity in philipp-zettl/chessPT 13 days ago

Training Date Size

1
#3 opened 14 days ago by
nh185285
reacted to schuler's post with πŸ”₯ 14 days ago
view post
Post
7217
πŸ“’ New Research Alert: Making Language Models Smaller & Smarter!

Thrilled to share the latest technical report demonstrating how to reduce language model parameters by 77% while maintaining performance.

The secret? Grouped pointwise convolutions. Yes. We brought a method from computer vision to the transformers arena.

πŸ”‘ Key Findings:
β€’ 77% parameter reduction.
β€’ Maintained model capabilities.
β€’ Improved generalization.

Paper: https://www.researchgate.net/publication/388835829_SAVING_77_OF_THE_PARAMETERS_IN_LARGE_LANGUAGE_MODELS_TECHNICAL_REPORT
Code: https://github.com/joaopauloschuler/less-parameters-llm
  • 2 replies
Β·