2 papers
cs.LG2025
Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs
Anshumann, Mohd Abbas Zaidi, Akhil Kedia +5
Knowledge distillation can be a cost-effective technique to distill knowledge in Large Language Models, if the teacher output logits can be pre-computed and cached. However, succes…
cs.CL2024
Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models
Akhil Kedia, Mohd Abbas Zaidi, Sushil Khyalia +3
In spite of their huge success, transformer models remain difficult to scale in depth. In this work, we develop a unified signal propagation theory and provide formulae that govern…