Commit Graph

74 Commits

Author SHA1 Message Date
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
a4fd976048 refactor dataset_attr, add eos in pt, fix #757
Former-commit-id: a9d1fb72f7
2023-09-01 19:00:45 +08:00
codemayq
c955d9267c add dataset stage check
Former-commit-id: f7fdc088d4
2023-08-30 16:23:08 +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
hiyouga
d05d535a58 fix #617
Former-commit-id: 5235b15c91
2023-08-21 18:16:11 +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
hiyouga
fceca0bb6a update training resuming
Former-commit-id: 58f13e22da
2023-08-18 01:41:17 +08:00
hoshi-hiyouga
49d4ae3704 Merge branch 'main' into main
Former-commit-id: 7252903245
2023-08-18 01:37:23 +08:00
hiyouga
66771352bb support bf16 ppo #551
Former-commit-id: d125218cde
2023-08-18 00:40:32 +08:00
hiyouga
caf4a61e21 fix ChatGLM2 ppo #527 #528
Former-commit-id: 9f4c2adc9a
2023-08-18 00:34:59 +08:00
hiyouga
623a34b16f fix generation bug #532
Former-commit-id: be21fc83f9
2023-08-17 22:21:34 +08:00
hiyouga
a46f277477 fix streaming in pt stage #548 #549
Former-commit-id: b0ed0dec5e
2023-08-17 17:59:26 +08:00
hiyouga
048f99354f fix generation
Former-commit-id: d9e62711a3
2023-08-16 22:39:54 +08:00
hiyouga
edc15c62fa fix system prompt
Former-commit-id: 7407d9daa1
2023-08-16 01:35:52 +08:00
hiyouga
a9ab8f71d7 fix ChatGLM RLHF
Former-commit-id: af6c011fcb
2023-08-15 11:19:20 +08:00
hiyouga
d15fe288df alert pad_token source
Former-commit-id: 80b4053602
2023-08-15 00:07:56 +08:00
hiyouga
2aa2c363ad fix ChatGLM lm_head #494
Former-commit-id: d019956808
2023-08-14 14:14:48 +08:00
hiyouga
6c9b035c0e web UI integrating RLHF
Former-commit-id: ec94274ca1
2023-08-14 10:48:47 +08:00
hiyouga
e75024fde3 fix #480
Former-commit-id: 2f2fd55d81
2023-08-14 00:23:56 +08:00
hiyouga
e1b43dfc7f tiny fix
Former-commit-id: 9dc6a296e3
2023-08-12 22:02:43 +08:00
hiyouga
bd611e0090 fix rope scaling
Former-commit-id: 8545c11c45
2023-08-12 22:00:01 +08:00
hiyouga
ba65dcb15e update readme
Former-commit-id: 1836c020c5
2023-08-12 21:00:11 +08:00
hiyouga
3f0a2d6adc support rope scaling, fix #475 #476 #478
Former-commit-id: fa940c17b8
2023-08-12 20:46:27 +08:00
hiyouga
7bd4c59b7e fix unusual output of 8bit models #278 #391
Former-commit-id: dd51c24203
2023-08-12 00:25:29 +08:00
hiyouga
79f4ba0d26 Release v0.1.6
Former-commit-id: a48cb0d474
2023-08-11 23:25:57 +08:00
hiyouga
abdfa26d06 support DPO training (2305.18290)
Former-commit-id: 3ec4351cfd
2023-08-11 03:02:53 +08:00
hiyouga
6404167ab7 support val set in streaming mode
Former-commit-id: d86ea314a1
2023-08-09 23:00:26 +08:00
niuba
53a89f53aa add last_checkpoint support
Former-commit-id: 2ec68d3398
2023-08-09 16:39:27 +08:00
hiyouga
b43f37ca19 fix sft trainer
Former-commit-id: df946e6949
2023-08-09 16:35:03 +08:00
hiyouga
77aa9853fb fix tokenizer #417
Former-commit-id: eecc4b2131
2023-08-08 23:59:41 +08:00
hiyouga
70b53d9503 fix bug
Former-commit-id: 4b841a6b35
2023-08-08 17:55:55 +08:00
hiyouga
c796c542c8 fix chatml template #408
Former-commit-id: a9980617f5
2023-08-08 17:44:39 +08:00
hiyouga
871f7de3d0 fix #376
Former-commit-id: 081345baca
2023-08-07 13:58:59 +08:00
hiyouga
77f6647e8f update trainer
Former-commit-id: 220175ab24
2023-08-07 13:34:35 +08:00
hiyouga
2faa1af4eb fix qwen eos token
Former-commit-id: e21ae01356
2023-08-06 13:31:17 +08:00
hiyouga
0328c0e07c fix mtloader
Former-commit-id: a0173c427d
2023-08-03 19:29:02 +08:00
hiyouga
788d1250c1 fix qwen inference
Former-commit-id: 2780792754
2023-08-03 16:31:55 +08:00
hiyouga
9c84c4ed5d support Qwen-7B, fix InternLM-7B inference
Former-commit-id: 87f8f830e2
2023-08-03 15:53:32 +08:00
hiyouga
91d178f14d fix webui
Former-commit-id: e23a3a366c
2023-08-03 12:43:12 +08:00
hiyouga
4242897b78 modify code structure
Former-commit-id: 08f180e788
2023-08-02 23:17:36 +08:00
hiyouga
4b8e4398bc fix PPO trainer
Former-commit-id: 1d8a1878ea
2023-08-02 19:10:23 +08:00