arxiv:2601.07767
Deqing Fu PRO
deqing
AI & ML interests
None yet
Recent Activity
updated
a model about 13 hours ago
deqing/llama-600M-v4-bigram updated
a model about 14 hours ago
deqing/llama-600M-v4-unigram updated
a model about 14 hours ago
deqing/llama-600M-v4-fivegram Organizations
models 61
deqing/llama-600M-v4-fivegram
0.6B • Updated
• 857
deqing/llama-600M-v4-isolate
0.6B • Updated
• 3.08k
deqing/llama-600M-v4-unigram
0.6B • Updated
• 1.39k
deqing/llama-600M-v4-bigram
0.6B • Updated
• 1.44k
deqing/llama-600M-v4-swap_numbers
Text Generation • 0.6B • Updated
• 1.86k
deqing/llama-600M-v4-isolate-old
Text Generation • 0.6B • Updated
• 1.27k
deqing/llama-600M-v4-original
Text Generation • 0.6B • Updated
• 2.38k
deqing/llama-300M-v3-muon-original
Text Generation • 0.3B • Updated
• 2.24k
deqing/llama-300M-v3-original
Text Generation • 0.3B • Updated
• 3.18k
deqing/llama-300M-v2-isolate
Text Generation • 0.3B • Updated
• 2.02k