Retentive Network: A Successor to Transformer for Large Language Models
Paper
•
2307.08621
•
Published
•
167
•
34
Sehyun Choi
syncdoth
AI & ML interests
Machine Learning / Deep Learning, NLP, Language Modeling, Controllable Generation, Constraint Modeling, Commonsense Reasoning, Knowledge Incorporation
Organizations
syncdoth's activity
commented
a
paper
10 months ago
Are Lora weights loaded?
2
#4 opened about 1 year ago
by
syncdoth
syncdoth