yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE_MASKED-sppo-0.5-cos-rmsp-5e-7-checkpoint-772
Text Generation
•
Updated
•
5
ds_chat_cosine_replace_dpo
dpotraining with replaced coding block ground truth
-
-
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE_MASKED-sppo-0.5-cos-rmsp-5e-7-checkpoint-1158
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE_MASKED-sppo-0.5-cos-rmsp-5e-7-checkpoint-386
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE_MASKED-sppo-0.01-cos-rmsp-5e-7-checkpoint-772
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE_MASKED-sppo-0.01-cos-rmsp-5e-7-checkpoint-1158
Text Generation • Updated • 9 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE_MASKED-sppo-0.01-cos-rmsp-5e-7-checkpoint-386
Text Generation • Updated • 6 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE-sppo-0.1-cos-rmsp-5e-7-checkpoint-772
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE-sppo-0.1-cos-rmsp-5e-7-checkpoint-1158
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE-sppo-0.1-cos-rmsp-5e-7-checkpoint-386
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE_MASKED-sppo-0.1-cos-rmsp-5e-7-checkpoint-772
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE_MASKED-sppo-0.1-cos-rmsp-5e-7-checkpoint-1158
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE_MASKED-sppo-0.1-cos-rmsp-5e-7-checkpoint-386
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE-sppo-0.5-cos-rmsp-5e-7-checkpoint-772
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE-sppo-0.5-cos-rmsp-5e-7-checkpoint-1158
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE-sppo-0.5-cos-rmsp-5e-7-checkpoint-386
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE-sppo-0.01-cos-rmsp-5e-7-checkpoint-772
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE-sppo-0.01-cos-rmsp-5e-7-checkpoint-1158
Text Generation • Updated • 5 -
yiran-wang3/ds_chat_cosine_replace_dpo-GT_REPLACE-sppo-0.01-cos-rmsp-5e-7-checkpoint-386
Text Generation • Updated • 5