10 13 1

Yuxian Gu

t1101675

https://t1101675.github.io/

AI & ML interests

Efficient methods for language models

Recent Activity

upvoted a paper 11 days ago

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

upvoted a paper about 1 month ago

Instruction Pre-Training: Language Models are Supervised Multitask Learners

new activity about 2 months ago

fla-hub/delta_net-1.3B-100B:DeltaNet-340M models

View all activity

Organizations

t1101675's activity

upvoted a paper 11 days ago

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

Paper • 2502.14866 • Published 17 days ago • 12

upvoted a paper about 1 month ago

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published Jun 20, 2024 • 90

New activity in fla-hub/delta_net-1.3B-100B about 2 months ago

DeltaNet-340M models

#1 opened about 2 months ago by

t1101675

updated a model 2 months ago

Data-Selection/data_scorer

Updated Jan 5 • 7

New activity in t1101675/PICL 2 months ago

Add model card

#1 opened 2 months ago by

nielsr

New activity in MiniLLM/SFT-OPT-1.3B 2 months ago

Difference between SFT and init models

#1 opened 2 months ago by

HyeongSoo

upvoted a paper 3 months ago

Byte Latent Transformer: Patches Scale Better Than Tokens

Paper • 2412.09871 • Published Dec 13, 2024 • 93

authored a paper 3 months ago

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published Dec 5, 2024 • 58

upvoted a paper 3 months ago

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published Dec 5, 2024 • 58

updated a dataset 4 months ago

MiniLLM/pile-tokenized

Updated Nov 14, 2024 • 61 • 1

New activity in MiniLLM/init-gpt2-120M 4 months ago

Adding `safetensors` variant of this model

#1 opened 4 months ago by

SFconvertbot

updated 9 models 4 months ago