Commit Graph

319 Commits

Author SHA1 Message Date
hiyouga
5377d0bf95 fix #896
Former-commit-id: 8632bff811
2023-09-14 18:37:34 +08:00
hiyouga
632fff02e0 fix #887
Former-commit-id: 8857e45602
2023-09-14 17:56:58 +08:00
mmbwf
6ded1725d9 Update utils.py
Fix parameters load error.

Former-commit-id: 30fb721f12
2023-09-14 15:38:04 +08:00
hiyouga
c8780205bc fix ppo save model
Former-commit-id: 7ba57d5b14
2023-09-12 16:25:29 +08:00
hiyouga
4e86462bad fix #762 #814
Former-commit-id: d4be857e23
2023-09-12 16:10:10 +08:00
hiyouga
8ac7ec0b48 tiny fix
Former-commit-id: 3b306478d4
2023-09-11 18:27:08 +08:00
hiyouga
4410387859 Release v0.1.8
Former-commit-id: ccb3553576
2023-09-11 17:31:34 +08:00
hiyouga
33bab0e7c1 update flashattn, fix ppo save model
Former-commit-id: 0fbece85a7
2023-09-11 17:25:36 +08:00
hiyouga
6a71361a54 remove PeftTrainer
Former-commit-id: b218c271ed
2023-09-10 22:23:23 +08:00
hiyouga
8ab5566dc0 support FlashAttention2
Former-commit-id: d8aa1404be
2023-09-10 20:43:56 +08:00
hiyouga
85aa16f6c6 fix #850
Former-commit-id: 815b92e698
2023-09-10 14:22:03 +08:00
hiyouga
f865d0bd51 fix lora target
Former-commit-id: a51b7c98ac
2023-09-09 17:04:45 +08:00
hiyouga
c818a7ff60 support lora target auto find
Former-commit-id: bca1a247bc
2023-09-09 15:38:37 +08:00
hiyouga
c6265e6969 fix chatglm2 tokenizer
Former-commit-id: d8d82ca281
2023-09-09 13:50:29 +08:00
hiyouga
43a20c67d4 fix bug in DPO data collator
Former-commit-id: 90bd085ae4
2023-09-08 20:45:07 +08:00
hiyouga
405df0f63d fix #761
Former-commit-id: b34797a845
2023-09-08 20:22:18 +08:00
hiyouga
9ed4bb63d4 change to right-padding, update reward score #803
Former-commit-id: 8ea32e4046
2023-09-08 20:04:31 +08:00
hiyouga
62941919e8 fix chatglm template
Former-commit-id: 8aaaa132d4
2023-09-08 14:45:58 +08:00
hiyouga
f225a71445 update requirements
Former-commit-id: f5351c18e1
2023-09-07 19:26:25 +08:00
hiyouga
091326dc9f fix #818
Former-commit-id: 5a9970dbef
2023-09-07 19:19:53 +08:00
hiyouga
5030f05126 add deepspeed check in PPO training
Former-commit-id: ed1c2c5557
2023-09-07 19:12:40 +08:00
hiyouga
e6fa0229f4 fix #809
Former-commit-id: e2bf7c3bad
2023-09-07 19:04:32 +08:00
hiyouga
f74b980650 fix baichuan templates
Former-commit-id: 85b1f6632a
2023-09-07 18:54:14 +08:00
hiyouga
51f662860d update baichuan2 template
Former-commit-id: 0531886e1f
2023-09-06 21:43:06 +08:00
hiyouga
f9aee17f9d add Baichuan2 models
Former-commit-id: 62ce65c628
2023-09-06 18:36:04 +08:00
Q
a46ffa68ff fix utils.py bug
Former-commit-id: a19fc2ebf7
2023-09-05 10:38:01 +08:00
hiyouga
3b5a9c60b6 fix #763
Former-commit-id: 370bdb6e43
2023-09-01 23:13:05 +08:00
hiyouga
a4fd976048 refactor dataset_attr, add eos in pt, fix #757
Former-commit-id: a9d1fb72f7
2023-09-01 19:00:45 +08:00
codemayq
ea74e5a81b update llama2 template
Former-commit-id: 0bcc489c42
2023-08-30 16:23:56 +08:00
codemayq
c955d9267c add dataset stage check
Former-commit-id: f7fdc088d4
2023-08-30 16:23:08 +08:00
codingma
00c3cd5454 Merge pull request #651 from hiyouga/feature-dataset_stage
add dataset stage

Former-commit-id: 9b4d16d040
2023-08-28 16:03:45 +08:00
codemayq
292abfd438 add text format dataset preview in webui
Former-commit-id: 24e68d29f2
2023-08-24 19:45:36 +08:00
codemayq
2b979d39f2 add stage in DatasetAttr
Former-commit-id: ba94c8729d
2023-08-23 20:54:53 +08:00
hiyouga
0d0232479f fix import error
Former-commit-id: 2de1a7610a
2023-08-23 20:45:03 +08:00
hiyouga
38080233a5 fix #649
Former-commit-id: 57146c101f
2023-08-23 20:21:15 +08:00
codemayq
4b29d9d2b0 add dataset stage and filter dataset when stage chosen in webui
Former-commit-id: c0e4d1e81b
2023-08-23 18:54:23 +08:00
hiyouga
2accde2cb7 fix webui
Former-commit-id: 1c702ad538
2023-08-23 11:03:35 +08:00
codemayq
433a96b8c2 fix quantization bit is ""
Former-commit-id: a7cc6c4140
2023-08-23 10:08:17 +08:00
codemayq
7b82ea708d fix quantization is ""
Former-commit-id: ec2047b064
2023-08-23 10:04:03 +08:00
hiyouga
802494e20a update template
Former-commit-id: 4318347d3f
2023-08-22 19:46:09 +08:00
hiyouga
d05d535a58 fix #617
Former-commit-id: 5235b15c91
2023-08-21 18:16:11 +08:00
hiyouga
e6f4eab4ab fix #608
Former-commit-id: 02d69b6fde
2023-08-21 17:49:36 +08:00
hiyouga
d3bef03dc6 fix baichuan template for training #597 #616
Former-commit-id: 0a3f698425
2023-08-21 17:41:51 +08:00
hiyouga
fa15416024 fix #595
Former-commit-id: 5c052836a0
2023-08-20 16:40:00 +08:00
beat4ocean
c81d1d40fa fix KeyError: 'lang' bug
Former-commit-id: 7b45de6b9f
2023-08-20 15:32:36 +08:00
hiyouga
570ccc3618 fix ppo trainer #551
Former-commit-id: 0676497104
2023-08-20 14:07:11 +08:00
hiyouga
acaac6df9e Release v0.1.7
Former-commit-id: 9c9009f49f
2023-08-18 17:21:27 +08:00
hiyouga
9f1688924d tiny fix
Former-commit-id: d75e377b0f
2023-08-18 13:07:35 +08:00
hiyouga
b88f0b396c support ppo score norm (trl 0.5.1.dev required)
Former-commit-id: 53e33418d0
2023-08-18 12:02:42 +08:00
hiyouga
03edfd07e7 fix PPO trainer #551 , update readme
Former-commit-id: 9020524418
2023-08-18 11:43:10 +08:00