365 Commits

Author SHA1 Message Date
hiyouga
df33548b39 update readme
Former-commit-id: 5581cb2e4e59f3f8109e2acd4611789f9e50bfca
2024-05-27 18:14:02 +08:00
seanzhang-zhichen
9c8d79fbe3 Merge branch 'main' into add_dataset_sample_num
Former-commit-id: 27cb51f7f86f97ae231abfdcb0114ff245d7af9c
2024-05-24 15:57:47 +08:00
hiyouga
3e729798df refactor data preprocessing, fix mllm rlhf
Former-commit-id: 3a023bca2a502810a436cfba7708df164754ea62
2024-05-24 04:08:25 +08:00
hiyouga
d3490aceb7 fix paligemma sft
requires transformers>=4.41.1


Former-commit-id: de0e67aff13f191fd899ad717ec349a6bdb14f2a
2024-05-24 00:23:40 +08:00
hiyouga
4ddc1c9c16 fix paligemma sft
Former-commit-id: 7134fb02bbdc9421f6c314ae176d5786a8cd768d
2024-05-21 20:03:09 +08:00
hiyouga
a935c5105d fix paligemma data preprocess
Former-commit-id: e55c85ac72f4938738dbce576f83b47a1fea88ae
2024-05-20 23:51:32 +08:00
hiyouga
446c681b58 fix paligemma inference
Former-commit-id: 542229abb3aba2032d4c52a878c0fd35ba299691
2024-05-20 23:36:43 +08:00
zhangzc
4b90f04c1f fix conflict
Former-commit-id: d956041640d9abc5e59919a227d27270fb513a7e
2024-05-20 17:10:01 +08:00
hiyouga
864da49139 fix chat engines
do not use pop(key, default) since api assigns None to dict values


Former-commit-id: d52fae2fa866afeb6156dc98388ce5cc6d5eca77
2024-05-20 00:36:43 +08:00
hiyouga
0e57bb201c fix jinja template
Former-commit-id: 10573e1639e7a71813927a8bfff3b036c21064c3
2024-05-19 23:38:30 +08:00
hiyouga
519d2511ae improve data process logger
Former-commit-id: a851056229f37391023627180b5712ed64ae3528
2024-05-18 22:02:42 +08:00
hiyouga
1e867c0fa0 fix #3803
Former-commit-id: 0edc16769f7e84b74e5fc6a1382e284632567c4c
2024-05-18 16:13:14 +08:00
hiyouga
13d7b48efe improve KTO impl., replace datasets
Former-commit-id: c450ee87a35ff9235f9b695b0de2e042b2971178
2024-05-18 03:44:56 +08:00
enji.zhou
03956053b8 add kto
Former-commit-id: db1d5a4f51faae61fe18666057353747b01f5b8d
2024-05-17 13:09:17 +08:00
hiyouga
cae823ddf0 rename package
Former-commit-id: 308edbc4260d45907b4a9d3a45ec21d83e48aacb
2024-05-16 18:39:08 +08:00