kmseong/llama2-7b-chat-gsm8k-safedelta-scale0.1_revised
Text Generation • 7B • Updated • 50
kimminseong
kmseong
AI & ML interests
None yet
Recent Activity
updated a model 6 days ago
kmseong/llama2-7b-chat-original-space-freeze-p20-lr5e-5 published a model 6 days ago
kmseong/llama2-7b-chat-original-space-freeze-p20-lr5e-5 updated a model 6 days ago
kmseong/llama2-7b-chat-original-space-freeze-p40-lr5e-5Organizations
None yet
kmseong/llama3_2_3b-instruct-MATH-safedelta-scale0.1_revised_2
Text Generation • 3B • Updated • 37
kmseong/llama3_2_3b-instruct-MATH-safedelta-scale0.1_revised
Text Generation • 3B • Updated • 40
kmseong/llama3_2_3b-instruct-gsm8k-safedelta-scale0.1_revised
Text Generation • 3B • Updated • 39
kmseong/llama2_7b_chat_gsm8k_resta_gamma0.3
7B • Updated • 76
kmseong/llama2-7b-chat-gsm8k-safedelta-scale0.1_origin_512samples
Text Generation • 7B • Updated • 33
kmseong/llama2-7b-chat-gsm8k-safedelta-scale0.1_origin
Text Generation • 7B • Updated • 40
kmseong/llama2-7b-chat-gsm8k-safedelta-scale0.1
Text Generation • 7B • Updated • 441
kmseong/llama2_7b_chat_gsm8k_ft_freeze_rsn_lr5e-5_new_revised
7B • Updated • 59
kmseong/llama2_7b_chat_gsm8k_ft_freeze_sn_lr5e-5_revised
7B • Updated • 70
kmseong/llama2_7b_chat_only_rsn_tuned_lr5e-5_revised
7B • Updated • 48
kmseong/llama2_7b_chat_only_sn_tuned_lr5e-5_revised
7B • Updated • 52
kmseong/llama2_7b_chat_gsm8k_ft_freeze_rsn_lr3e-5_new_revised
7B • Updated • 37
kmseong/llama2_7b_chat_only_rsn_tuned_lr3e-5_revised
7B • Updated • 42
kmseong/llama2_7b_only_sn_tuned_lr3e-5_revised
7B • Updated • 47
kmseong/llama2_7b-chat-SSFT-WaRP_medqa_FT_lr1e-5_fix
Text Generation • 7B • Updated • 12
kmseong/llama2_7b_chat-SSFT-MEDQA-FT-safety-mix-0.15-lr1e-5
7B • Updated • 30
kmseong/llama2_7b_chat_medqa_ft_freeze_rsn_lr1e-5
7B • Updated • 32
kmseong/llama2_7b_chat_medqa_ft_freeze_sn_lr1e-5
7B • Updated • 20
kmseong/llama2_7b_chat-SSFT-MEDQA-FT-safety-mix-0.1-lr1e-5_re
7B • Updated • 29
kmseong/llama2_7b_chat-SSFT-MEDQA-FT-lr1e-5
7B • Updated • 35
kmseong/llama2_7b_chat-SSFT-MEDQA-FT-safety-mix-0.1-lr1e-5
7B • Updated • 44
kmseong/llama2_7b_chat-SSFT-MEDQA-FT-safety-mix-0.1-lr3e-5
7B • Updated • 58
kmseong/llama2_7b-SSFT-WaRP_medqa_FT_lr3e-5-2
Text Generation • 7B • Updated • 300
kmseong/llama2_7b_chat_only_rsn_tuned_lr5e-5
7B • Updated • 23
kmseong/llama2_7b_base_medqa_ft_freeze_sn_lr3e-5
7B • Updated • 33
kmseong/llama2_7b-chat-SSFT-WaRP_medqa_FT_lr1e-5
Text Generation • 7B • Updated • 20
kmseong/llama2-7b-chat-medqa-safedelta-scale0.1
Text Generation • 7B • Updated • 287
kmseong/llama2_7b_only_sn_tuned_lr5e-5
7B • Updated • 37
kmseong/llama2_7b_chat_medaq_resta_gamma0.3
7B • Updated • 49