mikheevshow/SMOL_DPO_JS_DIVERGENCE-checkpoint-50
Text Generation • 0.1B • Updated
ILIA MIKHEEV
mikheevshow
·
AI & ML interests
None yet
Organizations
mikheevshow/SMOL_DPO_JS_DIVERGENCE-checkpoint-200
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_JS_DIVERGENCE-checkpoint-150
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_JS_DIVERGENCE-checkpoint-100
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_FORWARD_KL_0_1-checkpoint-50
Text Generation • 0.1B • Updated
mikheevshow/SMOL_DPO_FORWARD_KL_0_1-checkpoint-200
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_FORWARD_KL_0_1-checkpoint-150
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_FORWARD_KL_0_1-checkpoint-100
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_5_0-checkpoint-50
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_5_0-checkpoint-200
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_5_0-checkpoint-150
Text Generation • 0.1B • Updated
mikheevshow/SMOL_DPO_REVERSE_KL_5_0-checkpoint-100
Text Generation • 0.1B • Updated
mikheevshow/SMOL_DPO_REVERSE_KL_1_0-checkpoint-50
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_1_0-checkpoint-200
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_1_0-checkpoint-150
Text Generation • 0.1B • Updated
mikheevshow/SMOL_DPO_REVERSE_KL_1_0-checkpoint-100
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_0_1-checkpoint-50
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_0_1-checkpoint-200
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_0_1-checkpoint-150
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_0_1-checkpoint-100
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_0_05-checkpoint-50
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_0_05-checkpoint-200
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_0_05-checkpoint-150
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_REVERSE_KL_0_05-checkpoint-100
Text Generation • 0.1B • Updated
mikheevshow/SMOL_DPO_ALPHA_DIVERGENCE-checkpoint-50
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_ALPHA_DIVERGENCE-checkpoint-200
Text Generation • 0.1B • Updated
mikheevshow/SMOL_DPO_ALPHA_DIVERGENCE-checkpoint-150
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL_DPO_ALPHA_DIVERGENCE-checkpoint-100
Text Generation • 0.1B • Updated • 1
mikheevshow/SMOL2_DPO_FORWARD_KL
Text Generation • 0.1B • Updated
mikheevshow/SMOL2_DPO_ALPHA_DIVERGENCE
Text Generation • 0.1B • Updated