Jeesup/B3_tofu_Llama-3.2-1B-Instruct_forget10_QED_INT4LSQ_beta05
Text Generation • 1B • Updated • 6
Park
Jeesup
AI & ML interests
None yet
Recent Activity
published a dataset 5 days ago
Jeesup/glue-lora-bitwidth-results published a model 5 days ago
Jeesup/llama32-3B-rte-nf4-lora-seed44 published a model 5 days ago
Jeesup/llama32-3B-rte-nf4-lora-seed43Organizations
None yet
Jeesup/B3_tofu_Llama-3.2-1B-Instruct_forget10_QED_INT4LSQ_beta00
Text Generation • 1B • Updated • 6
Jeesup/A3_tofu_Llama-3.2-1B-Instruct_forget10_DurableUnSAF_INT4Sym_a30
Text Generation • 1B • Updated • 6
Jeesup/A3_tofu_Llama-3.2-1B-Instruct_forget10_DurableUnSAF_INT4Sym_a10
Text Generation • 1B • Updated • 4
Jeesup/A1_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_NoQAT
Text Generation • 1B • Updated • 9
Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_QAT_bnb4bit
1.0B • Updated • 7
Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_NPO_QAT
Text Generation • 1.0B • Updated • 5
Jeesup/tofu_Llama-3.2-3B-Instruct_forget10_NPO_QAT
Text Generation • 3B • Updated • 4
Jeesup/tofu_Llama-3.2-3B-Instruct_forget10_GradDiff_QAT
Text Generation • 3B • Updated • 6
Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_QAT
Text Generation • 1.0B • Updated • 6
Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_QAT_bnb8bit
Updated
Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_GradAscent_QAT_bnb8bit
Updated
Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_GradAscent_QAT_bnb4bit
Updated
Jeesup/tofu_Llama-3.2-3B-Instruct_forget10_RMU
Updated • 1
Jeesup/tofu_Llama-3.2-3B-Instruct_forget10_DPO
Updated
Jeesup/tofu_Llama-3.2-3B-Instruct_forget10_NPO
Updated
Jeesup/tofu_Llama-3.2-3B-Instruct_forget10_GradDiff
Updated
Jeesup/tofu_Llama-3.2-3B-Instruct_forget10_GradAscent
Updated
Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_RMU
Updated
Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_DPO
Updated
Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_NPO
Updated
Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_GradAscent
1B • Updated • 16
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 • 5
Jeesup/gemma_2_9b_cb_alpha10_layers10-20_lr1e-5_gsm8k_ftlr1e-5
9B • Updated • 5
Jeesup/gemma_2_9b_cb_alpha10_layers10-20_lr1e-5
9B • Updated • 2
Jeesup/gemma_2_9b_cb_alpha5_layers15-25_lr1e-5_gsm8k_ftlr1e-5
9B • Updated • 5
Jeesup/gemma_2_9b_cb_alpha5_layers15-25_lr1e-5
9B • Updated • 5
Jeesup/llama3_2_3b_cb_alpha10_layers15-25_lr1e-4
3B • Updated • 5