yunjae-won/4b-fwdkl-clip1e-6-lora_step25
Text Generation • 4B • Updated • 2
Yunjae Won
yunjae-won
AI & ML interests
None yet
Recent Activity
published a bucket 6 days ago
yunjae-won/Openthoughts_math_30k_opsd_clone published a model 6 days ago
yunjae-won/4b-fwdkl-clip1e-6-lora-adaKL-reg0.1_step25 published a model 6 days ago
yunjae-won/4b-fwdkl-clip1e-6-lora-adaKL-reg0.1_step100Organizations
yunjae-won/4b-fwdkl-clip1e-6-lora_step125
Text Generation • 4B • Updated • 2
yunjae-won/4b-fwdkl-clip1e-6-lora_step100
Text Generation • 4B • Updated • 2
yunjae-won/4b-fwdkl-clip1e-6-lora-staticKL-reg0.1_step75
Text Generation • 4B • Updated • 2
yunjae-won/4b-fwdkl-clip1e-6-lora-staticKL-reg0.1_step50
Text Generation • 4B • Updated • 2
yunjae-won/4b-fwdkl-clip1e-6-lora-staticKL-reg0.1_step25
Text Generation • 4B • Updated • 2
yunjae-won/4b-fwdkl-clip1e-6-lora-staticKL-reg0.1_step125
Text Generation • 4B • Updated • 2
yunjae-won/4b-fwdkl-clip1e-6-lora-staticKL-reg0.1_step100
Text Generation • 4B • Updated • 4
yunjae-won/4b-fwdkl-clip1e-6-lora-adaKL-reg0.1_step25
Text Generation • 4B • Updated • 9
yunjae-won/4b-fwdkl-clip1e-6-lora-adaKL-reg0.1_step100
Text Generation • 4B • Updated • 9
yunjae-won/4b-fwdkl-clip1e-6-lora-adaKL-reg0.1_step50
Text Generation • 4B • Updated • 10
yunjae-won/4b-fwdkl-clip1e-6-lora-adaKL-reg0.1_step75
Text Generation • 4B • Updated • 10
yunjae-won/4b-fwdkl-clip1e-6-lora-adaKL-reg0.1_step125
Text Generation • 4B • Updated • 9
yunjae-won/ubq30i_qwen4b_dpo_topk20_backprop_j001
Text Generation • 0.5B • Updated • 14
yunjae-won/ubq30i_qwen4b_dpo_topk20_j0
Text Generation • 0.5B • Updated • 13
yunjae-won/ubq30i_qwen4b_sft_both
Text Generation • 4B • Updated • 16
yunjae-won/ubq30i_qwen4b_sft_yw
Text Generation • 4B • Updated • 14
yunjae-won/ubq30i_qwen4b_sft_yl
Text Generation • 4B • Updated • 16
yunjae-won/ub_qwen4Bi_onlineDPO-w1e-2
Updated
yunjae-won/ub_qwen0.5Bi_onlineDPO-w1e-2
Updated
yunjae-won/ub_qwen0.5Bi_onlineDPO-w1e-1
Updated
yunjae-won/ub_qwen0.5Bi_onlineDPO-test
Updated
yunjae-won/ubq30i_qwen4b_sft-Online-DPO-test
Updated
yunjae-won/Qwen2.5-0.5B-Online-DPO-test
Updated
yunjae-won/mpq3_qwen4bi_sft
Text Generation • 4B • Updated • 6
yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step10240
Text Generation • 8B • Updated • 5
yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step9728
Text Generation • 8B • Updated • 7
yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step9216
Text Generation • 8B • Updated • 5
yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step8704
Text Generation • 8B • Updated • 6
yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step8192
Text Generation • 8B • Updated • 6