deqing/convergent-llama-300M-adamw-swap_numbers
Text Generation • 0.3B • Updated • 7
Deqing Fu PRO
deqing
AI & ML interests
None yet
Recent Activity
updated a model 25 days ago
deqing/convergent-llama-300M-muon-6digit-addition_6digit_custom6 upvoted a paper 27 days ago
Value-Aware Stochastic KV Cache Eviction for Reasoning Models submitted a paper 27 days ago
Value-Aware Stochastic KV Cache Eviction for Reasoning ModelsOrganizations
deqing/convergent-llama-300M-adamw-isolate
Text Generation • 0.3B • Updated • 7
deqing/convergent-llama-300M-adamw-unigram
Text Generation • 0.3B • Updated • 9
deqing/convergent-mamba2-300M-muon-original
Text Generation • 0.3B • Updated • 10
deqing/llama-window-4-old
Text Generation • 0.3B • Updated • 7
deqing/llama-window-2-old
Text Generation • 0.3B • Updated • 7
deqing/convergent-llama-300M-muon-unk_number
Text Generation • 0.3B • Updated • 5
deqing/convergent-llama-300M-muon-swap_numbers
Text Generation • 0.3B • Updated • 7
deqing/llama-isolate-old
Text Generation • 0.3B • Updated • 7
deqing/convergent-llama-300M-muon-fivegram
Text Generation • 0.3B • Updated • 7
deqing/convergent-llama-300M-muon-permute
Text Generation • 0.3B • Updated • 7
deqing/convergent-llama-300M-muon-bigram
Text Generation • 0.3B • Updated • 7
deqing/convergent-llama-300M-muon-unigram
Text Generation • 0.3B • Updated • 18
deqing/mamba2-300M-v5-mamba2
Text Generation • 0.3B • Updated • 19
deqing/lstm-12layer-v5
0.2B • Updated • 5
deqing/llama-300M-v5-original
Text Generation • 0.3B • Updated • 8
deqing/llama-300M-v5-unk_number
Text Generation • 0.3B • Updated • 7
deqing/llama-300M-v5-addition_3digit_adamw
0.3B • Updated • 2
deqing/llama-300M-v5-addition_3digit
0.3B • Updated • 2
deqing/llama-300M-v5-addition
Text Generation • 0.3B • Updated • 8
deqing/llama-300M-v5-addition_adamw
Text Generation • 0.3B • Updated • 7
deqing/llama-300M-v5-addition_adamw-old
0.3B • Updated • 1
deqing/llama-300M-v5-addition_3digit-old
0.3B • Updated • 2
deqing/llama-300M-v5-adamw-addition_3digit_adamw-old
0.3B • Updated • 2
deqing/llama-300M-v5-original-random_init_sft
Updated
deqing/llama-300M-v5-isolate_sft
Updated
deqing/llama-300M-v5-swap_numbers_sft
Updated
deqing/llama-300M-v5-addition-old
0.3B • Updated • 1
deqing/llama-300M-v5-original_sft
Updated
deqing/llama-300M-v5-bigram
Text Generation • 0.3B • Updated • 7