2764 Commits

Author SHA1 Message Date
hiyouga
9155401bf9 add belle multiturn dataset
Former-commit-id: 334d1a6d26a0c814b86bdfe68fe291c0513123fd
2023-06-16 20:01:16 +08:00
hiyouga
653ce9397e fix freeze layers
Former-commit-id: a6c4b141cd5e75a411277a0b43d9967a8abdaae6
2023-06-16 17:38:21 +08:00
hiyouga
36ea46e85c add source prefix
Former-commit-id: fc4d8155b35dcc453a64a50b21ce59050a15be99
2023-06-16 16:32:17 +08:00
hiyouga
c6d56e7109 support loading lora from hub
Former-commit-id: 0574b590ef3c4e317f7e2da25b0e5084dcef42a1
2023-06-16 00:02:17 +08:00
hiyouga
a68808d6d9 support baichuan model
Former-commit-id: 0cee6ad67ffb06f0d7165a0284e39f510a2abc36
2023-06-15 16:02:01 +08:00
hiyouga
50494db8d6 fix bug in template vanilla
Former-commit-id: c527399424d027a49d8584f4f7884eeabe5ea0df
2023-06-15 14:36:55 +08:00
hiyouga
64080d185e Update wechat.jpg
Former-commit-id: 0a36658bb6c532b55457196afb78867a6efd5ab9
2023-06-15 13:48:53 +08:00
hiyouga
dd1e7ed3cf add BOS token in pre-training
Former-commit-id: d668f8b501c367276ef4be372f2eb1753a1b7e86
2023-06-15 01:46:17 +08:00
hiyouga
3419396945 support multiturn training like FastChat
Former-commit-id: b6faf0207d5b637722a1fd45984d27b3ac095fd4
2023-06-14 22:27:39 +08:00
hiyouga
ca90a1e6d9 fix loading valuehead
Former-commit-id: 875e8e23498f6933d657ad154b53611310327e3e
2023-06-13 11:13:06 +08:00
hiyouga
c92bfb158f fix generating args
Former-commit-id: 531a3764d99ab00a0d217ce2ced0347b263dfe68
2023-06-13 01:33:56 +08:00
hiyouga
1fbda5d139 support RM metrics, add generating Args
Former-commit-id: cec6524d6b1be65c5d171a5b3dcaae7818132bc5
2023-06-12 15:48:48 +08:00
hoshi-hiyouga
5fe70c9350 Merge pull request #26 from BUAADreamer/main
add code for reading from multi files in one directory

Former-commit-id: e3f380c1be40a0fbbb784edf62698a6362cd2184
2023-06-11 19:06:29 +08:00
BUAADreamer
465264f852 update json line file to .jsonl
Former-commit-id: e3b53a67c7004769cbc6b3a17089f772687d9657
2023-06-11 18:59:19 +08:00
BUAADreamer
c4128832e5 add some
Former-commit-id: 676d910260f3bd0e360c40f8340f01b88a7fa06c
2023-06-11 18:55:53 +08:00
BUAADreamer
b1c6ee9cf5 add code for reading from multi files in one directory
Former-commit-id: a2af9df5a99ad529d0a280099b115cde69e02973
2023-06-10 16:27:30 +08:00
BUAADreamer
53727aee3e add code for reading from multi files in one directory
Former-commit-id: 3dd5f9a874d66353bb4379bbe39a89cd425dac3d
2023-06-10 15:53:47 +08:00
hiyouga
587d7a907f tiny fix
Former-commit-id: 2ba5d69c7f6e00e348c88b95331af9a80ede9561
2023-06-07 16:42:31 +08:00
hiyouga
fb9dedcb36 tiny fix
Former-commit-id: 16c2860d56581b90b20ad88631ddc3659ab7b56f
2023-06-07 16:02:07 +08:00
hiyouga
37c6234126 tiny fix
Former-commit-id: edafb977330767b82b6c9591d9ec180046155632
2023-06-07 12:58:14 +08:00
hiyouga
c43d3f2460 add templates
Former-commit-id: 3875b19a34c86e2cf1ab702e43840c42fac11d87
2023-06-07 12:40:44 +08:00
hiyouga
6e5414bf1d add belle template
Former-commit-id: 17acf3a3eba68d1fe3ec08b2ed91038560cab282
2023-06-07 12:30:11 +08:00
hiyouga
93f2e35035 tiny fix
Former-commit-id: ce43386080fa1535672f4d879ffe6c4360a1ef7d
2023-06-07 12:08:39 +08:00
hiyouga
ce08b4a7ec add prompt template class
Former-commit-id: 909af8f49698a1de3010becf61817cbedecf7879
2023-06-07 11:55:25 +08:00
hiyouga
4cd43f018b fix inference, add prompt template
Former-commit-id: 5d021d4ad514974dd9dcc5240871713cf53a87f2
2023-06-07 10:52:35 +08:00
hiyouga
8849bee763 recover logging
Former-commit-id: 13d1f0709c774bb5ec5fb2b4e3c66b2f1226afd2
2023-06-06 21:36:37 +08:00
hiyouga
794c2fd506 support distributed quantized training
Former-commit-id: 4eb17bcf6c8ac51a3ec8cc5459064d1b35c82634
2023-06-06 17:39:41 +08:00
hiyouga
1a49937351 add API demo from #1
Former-commit-id: 3d8d5ee5d54102dd73856fac3a80922ea3104a06
2023-06-05 21:32:18 +08:00
hoshi-hiyouga
2c34b7f858 Merge pull request #11 from hiyouga/api
Api

Former-commit-id: 06e1b120e1a8a399fc1f8b435667bd4d5418d75f
2023-06-05 20:58:02 +08:00
hiyouga
dc4d9e514e fix bug in web demo
Former-commit-id: a38d57ddd7fcbd2eb373e79f7236f8d2411c52d5
2023-06-05 17:58:29 +08:00
hiyouga
666fe30708 increase max length in cli demo
Former-commit-id: 56eb99106aa69eef8dab6b3518779db3373e639b
2023-06-05 16:49:14 +08:00
hiyouga
e92ac44cd2 implement stream generating
Former-commit-id: fe1d9308163699b7c4dd791915788855b2e6854f
2023-06-05 16:43:44 +08:00
hiyouga
e94cf814ff tiny fix
Former-commit-id: 44298c12355082740857ba650bf44a18d4d3b40d
2023-06-05 15:25:22 +08:00
hiyouga
b982a9df83 tiny fix
Former-commit-id: 38b83533a48e2f5a5817b8fc53a37554c42fd932
2023-06-04 16:35:50 +08:00
hiyouga
95a6f1759b tiny fix
Former-commit-id: eac9921e5cc7be2b686731f28b19983a07009128
2023-06-04 12:55:40 +08:00
hiyouga
4d4636c48e support QLoRA
Former-commit-id: 3b9eee8cd26cfeef945155815175831dec98eb20
2023-06-04 00:08:56 +08:00
hiyouga
08d6079140 fix int8 inference
Former-commit-id: 1bd13d7ca197edaa9a1143b061249b4fa6003b97
2023-06-03 23:22:05 +08:00
hiyouga
3bf4b20d0b reduce repetition penalty
Former-commit-id: 926291940de4b59a40489e6a509fdc0135c8616d
2023-06-03 21:57:39 +08:00
hiyouga
4200d5d558 fix int8 inference
Former-commit-id: 0f69a0c19ebe05ba6b2d66b56826b6df100e9f32
2023-06-03 21:17:47 +08:00
hiyouga
342ee89d28 add ziya prompt template
Former-commit-id: de09ee1315759a085e4fcf20e94963293c881aae
2023-06-03 19:05:51 +08:00
hiyouga
c7d71dd8af use low_cpu_mem_usage to speed up loading
Former-commit-id: 771f454ff1deee4929927c58feab7dcd3b854f9c
2023-06-03 18:19:01 +08:00
hiyouga
42c9c8de39 add logits processor
Former-commit-id: dca27b4412e8e41cadcd623582222e1c216db78b
2023-06-03 16:34:54 +08:00
hiyouga
1392242958 remove unused code
Former-commit-id: ed6161fa6a5f23dfacc52a2a77ddaeeb4adf8443
2023-06-03 00:10:54 +08:00
hiyouga
0f6efcc77a add wechat
Former-commit-id: 72a85ccc39e19a800cf638407fd3b53976a5af15
2023-06-02 21:47:10 +08:00
hiyouga
36790c4e32 tiny fix
Former-commit-id: b8a034807e97730bc95a5f0bf0ca0763d7c6824c
2023-06-02 19:02:25 +08:00
hiyouga
6ab22a0181 fix layer norm name in PPO
Former-commit-id: e3aaef7d4a37e4aa388a9158c382db8239843a5e
2023-06-02 17:30:01 +08:00
hiyouga
b0e9a673be fix #1
Former-commit-id: bd565af3706d74712e50884797ee2e2056a49809
2023-06-02 14:25:00 +08:00
hiyouga
4003ddcc3b alter rewards data type
Former-commit-id: 50d9a20f8103fcfb92a3e2a5e6f0055d27b29d53
2023-06-02 14:19:51 +08:00
hiyouga
7e1be4c21a fix possibly OOM error
Former-commit-id: e6126244c161dc87b0d4d45b8976c02fc9933545
2023-06-01 23:54:44 +08:00
hiyouga
3f3b475412 fix bug at inference
Former-commit-id: fd709eacff09d52636541cba009a1ded6aac22dc
2023-05-31 18:11:53 +08:00