Luiz Cesar Spies PRO
luizspies
ยท
AI & ML interests
None yet
Recent Activity
published an article about 2 months ago
What if you cached the model's hidden states instead of running it again? published an article 2 months ago
Transformer X-Ray: Attention Commitment Depth Across 6 Architectures published an article 2 months ago
X-raying a Transformer Forward PassOrganizations
None yet