Deqing Fu PRO

deqing

·

https://deqingfu.github.io

AI & ML interests

None yet

Recent Activity

authored a paper 5 days ago

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

upvoted a paper 5 days ago

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

submitted a paper 5 days ago

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

View all activity

Organizations

deqing 's models 158

deqing/lstm-window-4-v5

Text Generation • 0.2B • Updated Mar 19 • 13

deqing/llama-300M-v5-fivegram

Text Generation • 0.3B • Updated Mar 18 • 12

deqing/llama-300M-v5-base_7

Text Generation • 0.3B • Updated Mar 18 • 11

deqing/llama-300M-v5-permute

Text Generation • 0.3B • Updated Mar 17 • 11

deqing/llama-300M-v5-isolate-old

Text Generation • 0.3B • Updated Mar 16 • 11

deqing/test-fone-hub-upload

deqing/llama-600M-v4-isolate

Text Generation • 0.6B • Updated Mar 14 • 13

deqing/llama-600M-v4-fivegram

0.6B • Updated Mar 13 • 5

deqing/llama-600M-v4-bigram

Text Generation • 0.6B • Updated Mar 12 • 12

deqing/llama-600M-v4-unigram

0.6B • Updated Mar 11 • 3

deqing/mamba-370m-v4

deqing/llama-600M-v4-swap_numbers

Text Generation • 0.6B • Updated Mar 10 • 23

deqing/llama-600M-v4-isolate-old

Text Generation • 0.6B • Updated Mar 9 • 24

deqing/llama-600M-v4-original

Text Generation • 0.6B • Updated Mar 8 • 10

deqing/llama-300M-v3-muon-original

Text Generation • 0.3B • Updated Mar 6 • 12

deqing/llama-300M-v3-original

Text Generation • 0.3B • Updated Mar 5 • 12

deqing/llama-300M-v2-isolate

Text Generation • 0.3B • Updated Mar 2 • 55

deqing/llama-300M-v2-swap_numbers

Text Generation • 0.3B • Updated Mar 1 • 10

deqing/llama-300M-v2-fourgram

Text Generation • 0.3B • Updated Feb 28 • 12

deqing/llama-300M-v2-trigram

Text Generation • 0.3B • Updated Feb 28 • 10

deqing/llama-300M-v2-bigram

Text Generation • 0.3B • Updated Feb 28 • 12

deqing/llama-300M-v2-unigram

Text Generation • 0.3B • Updated Feb 27 • 14

deqing/llama-300M-v2-fivegram

Text Generation • 0.3B • Updated Feb 26 • 11

deqing/llama-300M-v2-text_only

Text Generation • 0.3B • Updated Feb 26 • 10

deqing/llama-300M-v2-uniform

Text Generation • 0.3B • Updated Feb 26 • 11

deqing/llama-300M-v2-original

Text Generation • 0.3B • Updated Feb 26 • 11

deqing/llama-300M-trigram

0.3B • Updated Feb 23

deqing/fone-llama-3.2-1B-fineweb-sample-100BT-fone3d-hybrid-tile-v3

deqing/fone-llama-3.2-1B-fineweb-sample-100BT-fone3d-hybrid-tile-v2

1B • Updated Feb 22 • 1

deqing/llama-300M-bigram

0.3B • Updated Feb 22 • 3