Deqing Fu PRO
deqing
AI & ML interests
None yet
Recent Activity
published a model less than a minute ago
deqing/convergent-llama-300M-adamw-addition_5digit published a model less than a minute ago
deqing/convergent-llama-300M-muon-addition_5digit updated a model about 3 hours ago
deqing/convergent-llama-300M-adamw-addition_4digitOrganizations
models 137
deqing/convergent-llama-300M-adamw-addition_5digit
Updated
deqing/convergent-llama-300M-muon-addition_5digit
Updated
deqing/fone-llama-3.2-1B-dclm-100BT-fone3d-hybrid-tile-v1
1B • Updated • 1.97k
deqing/convergent-llama-300M-muon-addition_4digit
0.3B • Updated
deqing/convergent-llama-300M-adamw-addition_4digit
0.3B • Updated
deqing/convergent-llama-300M-adamw-addition_2digit
Updated
deqing/convergent-llama-300M-muon-addition_2digit
Updated
deqing/vanilla-llama-3.2-1B-dclm-100BT-v1
1B • Updated • 2.11k • 1
deqing/vanilla-llama-3.2-1B-fineweb-sample-100BT-v4
1B • Updated • 210 • 1
deqing/vanilla-llama-3.2-1B-fineweb-sample-100BT-v4-old
Updated • 8