A 120B sparse MoE model with 460 experts was trained on one 8-GPU node to loss 1.78 using reversible recurrence and state-preserving scaling from a 1.78B dense seed, with 5.93B active parameters.
Qdylora: Quantized dynamic low- rank adaptation for efficient large language model tuning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2roles
background 1polarities
background 1representative citing papers
A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.
citing papers explorer
-
Reversible Foundations: Training a 120B Sparse MoE through State-Preserving Scaling
A 120B sparse MoE model with 460 experts was trained on one 8-GPU node to loss 1.78 using reversible recurrence and state-preserving scaling from a 1.78B dense seed, with 5.93B active parameters.
-
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.