Amr Hegazy

Amr-Hegazy

·

Amr-Hegazy1

AI & ML interests

None yet

Recent Activity

upvoted a paper 8 days ago

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

upvoted a paper 8 days ago

Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference

updated a collection 14 days ago

Gated Recurrent Transformer (GRT)

View all activity

Organizations

Amr-Hegazy 's models 5

Amr-Hegazy/grt-medium-isoparam

Text Generation • 0.2B • Updated 14 days ago • 250

Amr-Hegazy/grt-medium-isoflop

Text Generation • 0.4B • Updated 14 days ago • 257

Amr-Hegazy/grt-large-isoparam

Text Generation • 0.8B • Updated 14 days ago • 249

Amr-Hegazy/grt-large-isoflop

Text Generation • 0.3B • Updated 14 days ago • 266

Amr-Hegazy/ppo-LunarLander-v2

Reinforcement Learning • Updated Jan 16, 2025 • 2