Commit Graph

122 Commits

Author SHA1 Message Date
hiyouga
5a199af387 fix tokenizer for Yi chat models #1617 #1875
Former-commit-id: 71a9c16171
2023-12-18 17:18:11 +08:00
hiyouga
4e75ca1222 support dpo-ftx
Former-commit-id: b87c74289d
2023-12-16 19:21:41 +08:00
hiyouga
7dbc670902 support quantization in export model
Former-commit-id: 3524aa1e58
2023-12-15 23:44:50 +08:00
hiyouga
bd03307bbd refactor adapter hparam
Former-commit-id: 0716f5e470
2023-12-15 20:53:11 +08:00
hiyouga
15b321da8e remove loftq
Former-commit-id: 3a8a50d4d4
2023-12-13 01:53:46 +08:00
hiyouga
4c69025a83 support loftq
Former-commit-id: 6219dfbd93
2023-12-12 22:47:06 +08:00
hiyouga
1a0bdd305c support system column #1765
Former-commit-id: 0a9c6e0146
2023-12-12 19:45:59 +08:00
hiyouga
cefc0b2f03 fix modelscope data hub
Former-commit-id: d5b2c57a35
2023-12-12 18:33:06 +08:00
hoshi-hiyouga
b67085e13a Merge branch 'main' into feat/support_ms
Former-commit-id: 6382efec52
2023-12-12 17:55:32 +08:00
xingjun.wang
879209829e update args for MsDataset.load
Former-commit-id: 09533e95ed
2023-12-12 13:02:54 +08:00
hiyouga
bd28dd0fe6 update readme
Former-commit-id: 8cace77808
2023-12-12 11:44:30 +08:00
hiyouga
b641e9e97e fix #1784
Former-commit-id: 28d5de7e78
2023-12-09 20:53:18 +08:00
yuze.zyz
c523613f0a support ms dataset
Former-commit-id: 9c2247d700
2023-12-08 18:00:57 +08:00
hiyouga
1cb390b9b2 implement rm server #1543
Former-commit-id: 7df4f3ab20
2023-12-03 20:52:54 +08:00
hiyouga
c60e79c12e patch modelscope
Former-commit-id: bd42c229b0
2023-12-01 22:53:15 +08:00
hoshi-hiyouga
9a26819a58 Merge branch 'main' into feat/support_ms
Former-commit-id: 00f5c9ee16
2023-12-01 20:23:46 +08:00
hiyouga
e964fa7df7 fix err hint
Former-commit-id: a5a248d569
2023-12-01 17:13:22 +08:00
yuze.zyz
e08e0e5814 support ms
Former-commit-id: d38a2e7341
2023-11-29 20:36:55 +08:00
hiyouga
ae1048db6d fix #1659
Former-commit-id: 475a3fa0f4
2023-11-28 20:52:28 +08:00
hiyouga
b015ac35d8 support export size setting
Former-commit-id: 859a6ea942
2023-11-26 18:34:09 +08:00
hiyouga
f06c4c8f7a update ppo trainer
Former-commit-id: 5021062493
2023-11-20 21:39:15 +08:00
Yuchen Han
ec910a87c0 Update finetuning_args.py
Former-commit-id: b24635d22b
2023-11-17 00:15:51 -08:00
hiyouga
678052a7ef fix rlhf callback
Former-commit-id: 1817ffc86f
2023-11-16 03:26:19 +08:00
hiyouga
b71da932eb fix bug in PPO training
Former-commit-id: 856522a3df
2023-11-16 02:32:54 +08:00
hiyouga
f441932bd1 support full-parameter PPO
Former-commit-id: ce78303600
2023-11-16 02:08:04 +08:00
hiyouga
e30290444a support multiple modules in freeze training #1514
Former-commit-id: 4907452d95
2023-11-15 17:08:18 +08:00
hiyouga
8387f3011c fix #1494
Former-commit-id: d125ef5535
2023-11-14 18:07:20 +08:00
hiyouga
125587b187 refactor evaluation, upgrade trl to 074
Former-commit-id: 442aefb925
2023-11-13 22:20:35 +08:00
hiyouga
55e097aaac add todo
Former-commit-id: a0c31c68c4
2023-11-10 14:38:18 +08:00
hiyouga
6ee32cf71c tiny fix
Former-commit-id: 415bca900e
2023-11-09 17:20:49 +08:00
Yanqing
fc05fd52cf Update finetuning_args.py
更新 chatglm/falcon/bloom 的 lora_target 的名称

Former-commit-id: 3684dffa14
2023-11-09 17:04:40 +08:00
hiyouga
91f406cc99 fix ppo train and dpo eval
Former-commit-id: 01260d9754
2023-11-07 22:48:51 +08:00
hiyouga
1f2c56bff9 delete file
Former-commit-id: 479d0af2dc
2023-11-07 16:20:12 +08:00
hiyouga
3d40bdb600 upgrade peft, fix #1088 #1411
Former-commit-id: b2a60905f3
2023-11-07 16:13:36 +08:00
hiyouga
a9db89a025 update data readme (zh)
Former-commit-id: cc8ffa10d8
2023-11-02 23:42:49 +08:00
hiyouga
a1b0655457 support sharegpt format, add datasets
Former-commit-id: a837172413
2023-11-02 23:10:04 +08:00
hiyouga
15cef791ba fix #1356
Former-commit-id: dff128c7e3
2023-11-02 16:51:52 +08:00
hiyouga
22b3c913e9 fix #1325
Former-commit-id: 083787dbfe
2023-11-01 23:38:49 +08:00
hiyouga
fcfcac4858 support dataset cache
Former-commit-id: 3fe7df628d
2023-10-26 21:48:45 +08:00
hiyouga
d6c77d9196 reimplement neftune
Former-commit-id: 7b4acf7265
2023-10-22 16:15:08 +08:00
anvie
3635823fbe add NEFTune optimization
Former-commit-id: 57fb40aa04
2023-10-21 13:24:10 +07:00
hiyouga
95697652f1 fix #1232
Former-commit-id: b665e9e133
2023-10-20 23:28:52 +08:00
hiyouga
4930118761 fix #1218
Former-commit-id: 7a11a42dfd
2023-10-19 16:17:41 +08:00
hiyouga
f3fa47fa7d refactor export, fix #1190
Former-commit-id: ea82f8a82a
2023-10-15 16:01:48 +08:00
hiyouga
e585c789ce fix #1184
Former-commit-id: af18b0dce7
2023-10-14 19:20:11 +08:00
hiyouga
2562376f84 fix ppo args
Former-commit-id: 11bd271364
2023-10-11 23:40:50 +08:00
hiyouga
c9d1cd108d refactor model_dtype, fix PPO trainer
Former-commit-id: 2818af0b09
2023-10-11 23:16:01 +08:00
hiyouga
deb17942ab fix layer norm dtype
Former-commit-id: 84b7486885
2023-09-28 00:25:55 +08:00
hiyouga
927ff702ff refactor finetuning Args
Former-commit-id: 620efe1d8d
2023-09-27 22:28:06 +08:00
hiyouga
108c31e1fc support LongLoRA
Former-commit-id: 90375f600d
2023-09-27 21:55:50 +08:00