compress - a Tempo14 Collection

Tempo14 's Collections

Tools

Summary

QA

Traffic

Code

Prompt Engineering

Mixture of Experts

motion

chain of thought

robotic

new architecture

outperform gpt-4

RLHF

fast

efficient inference

agents

Synthetic Dataset

mamba

Instruction Tuning

reinforcement learning

Self Improvement

Inpaint

vision

Linear

3D

Math

RAG

Stable Diffusion

Merging

Memory

Spaces

Yolo

Music

compress

updated Mar 7

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Paper • 2403.03853 • Published Mar 6 • 61