kmseong/qwen2_5_32b_instruct_gsm8k_full_finetune_after_ssft_lr5e-5
33B • Updated • 78
kimminseong
kmseong
AI & ML interests
None yet
Recent Activity
updated a model about 2 hours ago
kmseong/llama2_7b-chat-medqa-safelora-r16-a32-lr2e-4-cb-thr0.5 published a model about 2 hours ago
kmseong/llama2_7b-chat-medqa-safelora-r16-a32-lr2e-4-cb-thr0.5 updated a model about 2 hours ago
kmseong/llama2_7b-chat-arc-safelora-r16-a32-lr2e-4-cb-thr0.5Organizations
None yet
kmseong/qwen2_5_32b_instruct_SSFT-lr5e-5
Text Generation • 33B • Updated • 90
kmseong/llama2-7b-chat-original-space-freeze-p20-lr5e-5
Text Generation • 7B • Updated • 5
kmseong/llama2-7b-chat-original-space-freeze-p40-lr5e-5
Text Generation • 7B • Updated • 6
kmseong/llama2-7b-chat-original-space-freeze-p25-lr5e-5
Text Generation • 7B • Updated • 4
kmseong/llama2-7b-chat-original-space-freeze-p30-lr5e-5
Text Generation • 7B • Updated • 5
kmseong/llama2-7b-chat-original-space-freeze-p50-lr5e-5
Text Generation • 7B • Updated • 5
kmseong/llama2-7b-chat-original-space-freeze-p10-lr5e-5
Text Generation • 7B • Updated • 5
kmseong/llama2_7b-chat-gsm8k_ssft_lr5e-5_final_experiment
7B • Updated • 4
kmseong/llama3.1-8b-base-gsm8k-safeinstr-ratio_10p-lr1e-5
Text Generation • 8B • Updated • 58
kmseong/llama3.1-8b-base-warp-gsm8k-lr1e-5
Text Generation • 8B • Updated • 56
kmseong/llama3.1-8B_base_gsm8k_ft_freeze_rsn_lr1e-5
8B • Updated • 47
kmseong/llama3.1-8B_base_gsm8k_ft_freeze_sn_lr1e-5
8B • Updated • 50
kmseong/llama3.1-8b-base-gsm8k-resta-gamma0.3-lr1e-5
Text Generation • 8B • Updated • 55
kmseong/llama3.1-8b-base-gsm8k-safedelta-scale0.1-lr1e-5
Text Generation • 8B • Updated • 59
kmseong/Llama-3.1-8B-base-gsm8k-SSFT_lr1e-5
Text Generation • 8B • Updated • 13
kmseong/llama2-7b-chat-lr1e-5-mmlu-safeinstr-lr5e-5-ratio0.1
Text Generation • 7B • Updated • 7
kmseong/llama2_7b_chat_mmlu_freeze_rsn_lr5e-5
Text Generation • 7B • Updated • 6
kmseong/llama2-7b-chat-lr5e-5-mmlu-resta-gamma0.3
Text Generation • 7B • Updated • 5
kmseong/llama2-7b-chat-lr5e-5-mmlu-safedelta-scale0.1
Text Generation • 7B • Updated • 4
kmseong/llama2-7b-chat-lr5e-5-mmlu-lr5e-5
Text Generation • 7B • Updated • 8
kmseong/llama2-7b-chat-WaRP-mmlu-lr5e-5
Text Generation • 7B • Updated • 5
kmseong/llama2_7b_chat_mmlu_freeze_sn_lr5e-5
Text Generation • 7B • Updated • 6
kmseong/llama-2-7b-gsm8k-rsn-tuned-lr5e-5
7B • Updated • 4
kmseong/llama-2-7b-gsm8k-sn-tuned-lr5e-5
7B • Updated • 3
kmseong/llama-2-7b-only-rsn-tuned-lr5e-5
7B • Updated • 4
kmseong/llama-2-7b-only-sn-tuned-lr5e-5
7B • Updated • 5
kmseong/llama2_13b_chat_gsm8k_ft_freeze_sn_rotation_space_lr5e-5
13B • Updated • 50
kmseong/llama2_13b_chat_only_sn_tuned_rotation_space_lr5e-5
13B • Updated • 6
kmseong/Llama-2-7b-chat-hf_gsm8k_ft_freeze_basis_rotation_rsn_lr5e-5
7B • Updated • 3