Deqing Fu PRO
deqing
AI & ML interests
None yet
Recent Activity
authored a paper about 3 hours ago
Convergent Evolution: How Different Language Models Learn Similar Number Representations updated a model about 13 hours ago
deqing/vanilla-llama-3.2-1B-dclm-100BT-v1 upvoted a collection about 17 hours ago
Convergent EvolutionOrganizations
models 130
deqing/vanilla-llama-3.2-1B-dclm-100BT-v1
1B • Updated • 939 • 1
deqing/vanilla-llama-3.2-1B-fineweb-sample-100BT-v4
1B • Updated • 646 • 1
deqing/vanilla-llama-3.2-1B-fineweb-sample-100BT-v4-old
Updated • 8
deqing/fone-llama-3.2-1B-fineweb-sample-100BT-fone3d-hybrid-tile-v4
Updated • 1.44k • 3
deqing/convergent-llama-300M-muon-isolate-8
Text Generation • 0.3B • Updated • 2.26k • 1
deqing/convergent-llama-300M-muon-isolate-2
Text Generation • 0.3B • Updated • 1.3k
deqing/convergent-llama-300M-muon-window-2
Text Generation • 0.3B • Updated • 3.39k
deqing/convergent-llama-300M-muon-window-64
Text Generation • 0.3B • Updated • 1.27k • 1
deqing/convergent-llama-300M-muon-isolate-1
Text Generation • 0.3B • Updated • 1.48k
deqing/convergent-llama-300M-muon-window-8
Text Generation • 0.3B • Updated • 2.02k