AI & ML interests
None yet
Organizations
None yet
Boko99/qwen2_ca_dpo_Lc_0.5_Lu_0.5
Updated
Boko99/qwen2_ca_dpo_Lc_0.5_Lu_0.1
Updated
Boko99/qwen2_ca_dpo_Lc_0.3_Lu_0.3
Updated
Boko99/qwen2_ca_dpo_Lc_0.1_Lu_0.3
Updated
Boko99/qwen2_ca_dpo_wo_Lu
Updated
Boko99/qwen2_ca_dpo_wo_Lc
Updated
Boko99/llava_ca_dpo_Lc_0.5_Lu_0.5
Updated
Boko99/llava_ca_dpo_Lc_0.3_Lu_0.3
Updated
Boko99/llava_ca_dpo_Lc_0.3_Lu_0.1
Updated
Boko99/llava_ca_dpo_Lc_0.1_Lu_0.5
Updated
Boko99/llava_ca_dpo_wo_Lu
Updated
Boko99/llava_ca_dpo_wo_Lc
Updated
Boko99/llava_ca_dpo_Lp_0.5_Lu_0.5
Updated
Boko99/llava_ca_dpo_Lp_0.3_Lu_0.3
Updated
Boko99/llava_ca_dpo_Lp_0.3_Lu_0.1
Updated
Boko99/llava_ca_dpo_Lp_0.1_Lu_0.5
Updated
Boko99/Qwen2_VL_Instruct_2B_CA_DPO_CFG_Lp_0.1_a_0.5
Updated
Text Generation
•
266k
•
Updated
Boko99/llama3-instruct-simpo
Text Generation
•
266k
•
Updated
Boko99/Llama-3-8B-Instruct-Base-SimPO-wo-prompt-QLoRA-r16-llama3-ultrafeedback-5e6
Updated
Boko99/Llama-3-8B-Instruct-Base-SimPO-wo-prompt-QLoRA-r16-llama3-ultrafeedback-1e5
Updated