arxiv:2403.15042
Sehoon Kim
kssteven
AI & ML interests
Efficient AI, AI Systems, Model Compression
Recent Activity
upvoted a paper about 21 hours ago
ResidualQuant: KV Cache Quantization for Looped Transformers with 2-Bit Residuals liked a model 10 days ago
SketchSSM/Nemotron-Nano-9B-v2-BF16 liked a model 10 days ago
SketchSSM/Nemotron-3-Super-NVFP4Organizations
models 17
kssteven/mT5-small-wmt2014-calm-ft
Updated • 6
kssteven/mT5-small-iwslt2017-calm-ft
Updated • 7
kssteven/T5-small-cnndm-bild-aligned
Updated • 5
kssteven/T5-large-cnndm
Updated • 17
kssteven/T5-small-cnndm
Updated • 14
kssteven/T5-small-xsum-bild-aligned
Updated • 128
kssteven/T5-small-xsum
Updated • 113
kssteven/T5-large-xsum
Updated • 178
kssteven/mT5-small-wmt2014-de-en-bild-aligned
Updated • 7
kssteven/mT5-small-wmt2014-de-en
Updated • 4
datasets 0
None public yet