selfcorrexp/llama3_starplus_test2_ep3tmp07
Viewer
•
Updated
•
15k
•
10
AI & ML interests
None defined yet.
selfcorrexp/llama3_starplus_test2_ep3tmp10
Viewer
•
Updated
•
15k
•
14
selfcorrexp/distill_40koldc2r_120kw_84kcorr
Viewer
•
Updated
•
204k
•
14
selfcorrexp/distill_0kc2r_120kw_84kcorr
Viewer
•
Updated
•
204k
•
14
selfcorrexp/llama3_starplus_test2tmp07
Viewer
•
Updated
•
15k
•
11
selfcorrexp/llama3_starplus_test2tmp10
Viewer
•
Updated
•
15k
•
10
selfcorrexp/distill_40kc2r_120kw_84kcorr
Viewer
•
Updated
•
244k
•
15
selfcorrexp/llama3_it_distill_first_corr_c2r
Viewer
•
Updated
•
84.4k
•
13
selfcorrexp/llama3_it_distill_first_wrong
Viewer
•
Updated
•
205k
•
12
selfcorrexp/llama3_it_distill_first_corr
Viewer
•
Updated
•
84.4k
•
11
selfcorrexp/llama3_it_first_corr_merged
Viewer
•
Updated
•
87k
•
10
selfcorrexp/llama3_it_firstwrong_try2_merged
Viewer
•
Updated
•
110k
•
10
selfcorrexp/llama3_it_1wrong_70bcollect_merged
Viewer
•
Updated
•
118k
•
14
selfcorrexp/llama3_it_first_corr
Viewer
•
Updated
•
174k
•
11
selfcorrexp/llama3_it_firstwrong_try2
Viewer
•
Updated
•
330k
•
12
selfcorrexp/llama3_it_1wrong_70bcollect
Viewer
•
Updated
•
354k
•
11
selfcorrexp/llama3_starplus_testtmp07
Viewer
•
Updated
•
15k
•
7
selfcorrexp/llama3_starplus_testtmp10
Viewer
•
Updated
•
15k
•
10
selfcorrexp/llama3_rr40k_2e6_bz32_ep2_moredatatmp10_gold_reward
Viewer
•
Updated
•
15k
•
10
selfcorrexp/llama3_rr40k_2e6_bz32_ep2_moredatatmp10
Viewer
•
Updated
•
15k
•
9
selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_newtype1andtype2
Viewer
•
Updated
•
23.8k
•
10
selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_newtype2
Viewer
•
Updated
•
9.31k
•
10
selfcorrexp/llama3_non_delete_rr40k_3ep_dpo_newtype1
Viewer
•
Updated
•
14.5k
•
14
selfcorrexp/dpo_final_scalingtmp07_with_rewards
Viewer
•
Updated
•
325k
•
8
selfcorrexp/dpo_final_scalingtmp07
Viewer
•
Updated
•
325k
•
6
selfcorrexp/type12_8ktype4_2ktype3_new_350tmp10
Viewer
•
Updated
•
15k
•
13
selfcorrexp/type12_type4_8b_type3_1k_cut_separate_pr
Viewer
•
Updated
•
34.8k
•
7
selfcorrexp/type12_type4_8b_type3_3k_cut_separate_pr
Viewer
•
Updated
•
34.8k
•
10
selfcorrexp/type12_type4_8b_type3_4k_cut_separate_pr
Viewer
•
Updated
•
35.8k
•
10
selfcorrexp/type12_type4_8b_type3_2k_cut_separate_pr
Viewer
•
Updated
•
33.8k
•
7