Matthias Seeger
mseeger
·
AI & ML interests
None yet
Recent Activity
new activity
about 15 hours ago
deepseek-ai/DeepSeek-V2:Exact computations for multi-head latent attention
new activity
about 2 months ago
Isotonic/gpt_neox_225M:hidden_size % num_attention_heads != 0
Organizations
None yet
mseeger's activity
Exact computations for multi-head latent attention
1
#9 opened about 15 hours ago
by
mseeger
hidden_size % num_attention_heads != 0
#2 opened about 2 months ago
by
mseeger