Deqing Fu's picture

Deqing Fu PRO

deqing

·

https://deqingfu.github.io

AI & ML interests

None yet

Recent Activity

published a model 31 minutes ago

deqing/llama-300M-v5-adamw-addition_3digit_adamw

published a model 32 minutes ago

deqing/llama-300M-v5-isolate

published a model about 1 hour ago

deqing/llama-300M-v5-addition_3digit

View all activity

Organizations

Papers 14

arxiv:2601.07767

arxiv:2510.19753

arxiv:2507.16746

arxiv:2506.09967

models 80

deqing/llama-300M-v5-addition_adamw

0.3B • Updated 26 minutes ago

deqing/llama-300M-v5-adamw-addition_3digit_adamw

Updated 31 minutes ago

deqing/llama-300M-v5-isolate

Updated 32 minutes ago

deqing/llama-300M-v5-addition

0.3B • Updated 41 minutes ago

deqing/llama-300M-v5-addition_3digit

Updated about 1 hour ago

deqing/llama-300M-v5-original_sft

Updated about 10 hours ago

deqing/llama-300M-v5-unigram

Text Generation • 0.3B • Updated about 15 hours ago • 1.38k

deqing/llama-300M-v5-bigram

Text Generation • 0.3B • Updated about 16 hours ago • 1.38k

deqing/lstm-window-4-v5

Text Generation • 0.2B • Updated 1 day ago • 1.66k

deqing/fone-llama-3.2-1B-fineweb-sample-100BT-fone3d-hybrid-tile-v4

1B • Updated 1 day ago • 263

datasets 3

deqing/addition_dataset

Viewer • Updated about 1 hour ago • 1.08B • 150

deqing/minipile

Viewer • Updated Oct 29, 2025 • 100k • 41

deqing/minipile_demo

Viewer • Updated Oct 28, 2025 • 11.7k • 81