Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_GradAscent
1B • Updated • 22
Park
Jeesup
AI & ML interests
None yet
Recent Activity
updated a model 34 minutes ago
Jeesup/tofu_1B_f10_RMU_lr1e-5_sc10 updated a model about 1 hour ago
Jeesup/tofu_1B_f10_RMU_lr1e-5_sc1 updated a model about 4 hours ago
Jeesup/tofu_1B_f10_RMU_lr1e-4_sc5Organizations
None yet
Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_GradDiff
Updated • 1
Jeesup/gemma_2_9b_cb_alpha10_layers15-25_lr1e-5_gsm8k_ftlr1e-5
Updated
Jeesup/gemma_2_9b_cb_alpha10_layers15-25_lr1e-5
9B • Updated • 19
Jeesup/gemma_2_9b_cb_alpha10_layers10-20_lr1e-5_gsm8k_ftlr1e-5
9B • Updated • 32
Jeesup/gemma_2_9b_cb_alpha10_layers10-20_lr1e-5
9B • Updated • 26
Jeesup/gemma_2_9b_cb_alpha5_layers15-25_lr1e-5_gsm8k_ftlr1e-5
9B • Updated • 38
Jeesup/gemma_2_9b_cb_alpha5_layers15-25_lr1e-5
9B • Updated • 15
Jeesup/llama3_2_3b_cb_alpha10_layers15-25_lr1e-4
3B • Updated • 15
Jeesup/gemma_2_9b_cb_alpha5_layers10-20_lr1e-5_gsm8k_ftlr1e-5
9B • Updated • 38
Jeesup/llama3_2_3b_cb_alpha10_layers10-20_lr1e-5_gsm8k_ftlr5e-5
3B • Updated • 27
Jeesup/llama3_2_3b_cb_alpha10_layers10-20_lr1e-5
3B • Updated • 16
Jeesup/llama3_2_3b_cb_alpha10_layers10-20_lr5e-5_gsm8k_ftlr5e-5
3B • Updated • 25
Jeesup/gemma_2_9b_cb_alpha5_layers10-20_lr1e-5
9B • Updated • 26
Jeesup/llama3_2_3b_cb_alpha10_layers10-20_lr5e-5
3B • Updated • 16
Jeesup/llama3_2_3b_cb_alpha10_layers10-20_lr1e-4_gsm8k_ftlr5e-5
3B • Updated • 25
Jeesup/llama3_2_3b_cb_alpha10_layers10-20_lr1e-4
3B • Updated • 22
Jeesup/llama3_2_3b_cb_alpha5_layers15-25_lr1e-5_gsm8k_ftlr5e-5
3B • Updated • 27
Jeesup/llama3_2_3b_cb_alpha5_layers15-25_lr1e-5
3B • Updated • 9
Jeesup/llama3_2_3b_cb_alpha5_layers15-25_lr5e-5_gsm8k_ftlr5e-5
3B • Updated • 26
Jeesup/llama3_2_3b_cb_alpha5_layers15-25_lr5e-5
3B • Updated • 15
Jeesup/gemma_2_9b_cb_alpha10_layers20-30_lr1e-5_gsm8k_ftlr5e-5
9B • Updated • 26
Jeesup/llama3_2_3b_cb_alpha5_layers15-25_lr1e-4_gsm8k_ftlr5e-5
3B • Updated • 24
Jeesup/llama3_2_3b_cb_alpha5_layers15-25_lr1e-4
3B • Updated • 14
Jeesup/gemma_2_9b_cb_alpha10_layers20-30_lr1e-5
9B • Updated • 14
Jeesup/llama3_2_3b_cb_alpha5_layers10-20_lr1e-5_gsm8k_ftlr5e-5
3B • Updated • 34
Jeesup/llama3_2_3b_cb_alpha5_layers10-20_lr1e-5
3B • Updated • 14
Jeesup/gemma_2_9b_cb_alpha10_layers20-30_lr5e-5_gsm8k_ftlr5e-5
9B • Updated • 26
Jeesup/llama3_2_3b_cb_alpha5_layers10-20_lr5e-5_gsm8k_ftlr5e-5
3B • Updated • 25
Jeesup/llama3_2_3b_cb_alpha5_layers10-20_lr5e-5
3B • Updated • 14