hiyouga
|
baf2e4e825
|
a monkey patch for lora_target
Former-commit-id: 622f44a05b49b10571bd189ae3843683117ad77f
|
2023-07-18 00:31:40 +08:00 |
|
hiyouga
|
eac7f97337
|
release v0.1.0
Former-commit-id: 63c8d3a17cb18f0d8a8e37bfa147daf5bdd28ea9
|
2023-07-18 00:18:25 +08:00 |
|
hiyouga
|
c08ff734a7
|
fix #175
Former-commit-id: fd557ebb5e3ef2ca330b4d97731af43f4a5a5fc5
|
2023-07-17 18:07:17 +08:00 |
|
hiyouga
|
e9736b2ba0
|
fix saving custom code
Former-commit-id: 3f8f40bffd4f61fcc045f5f8a07420f3b46d0f7a
|
2023-07-16 18:04:41 +08:00 |
|
hiyouga
|
f8831cb1ea
|
fix callback
Former-commit-id: 477ef5ffd84c78ab1a8bce27714bb4f6e6ca0210
|
2023-07-15 22:01:43 +08:00 |
|
hiyouga
|
6a0499ef40
|
update stream_chat
Former-commit-id: e57b2152cf1d5c9e481523e36be4ed09b88e1285
|
2023-07-15 19:51:02 +08:00 |
|
hiyouga
|
a8deee27f8
|
create chat model
Former-commit-id: bddf583b2fc099c957a1037418bd8504a837663e
|
2023-07-15 19:26:20 +08:00 |
|
hiyouga
|
e9fe48150c
|
Update callbacks.py
Former-commit-id: 44ebe58083dc62128fd14df474c11c6e09af43db
|
2023-07-15 17:39:16 +08:00 |
|
hiyouga
|
a31a609377
|
fix callback
Former-commit-id: 065680cd2a410d7ceab10a4a76588df43e286117
|
2023-07-15 17:18:16 +08:00 |
|
hiyouga
|
6261fb362a
|
modity code structure
Former-commit-id: 0682ed357210897e0b67c4a6eb31a94b3eb929f1
|
2023-07-15 16:54:28 +08:00 |
|
hiyouga
|
fa06b168ab
|
fix eval and pred loss
Former-commit-id: 2a5a8e0eba279de603c2d25e894b6d2921aaae55
|
2023-07-14 13:11:57 +08:00 |
|
hiyouga
|
961e6a9ba4
|
fix pretrain
Former-commit-id: 75b584875fc75c437491a5155ef310248e9b9dd4
|
2023-07-13 23:41:54 +08:00 |
|
hiyouga
|
316a02696f
|
fix Baichuan-13B
Former-commit-id: 6d9d826b3246349454c68f4d13b862da4de986e2
|
2023-07-13 23:08:45 +08:00 |
|
Jinghuan Shang
|
30b2092294
|
Fix typo in common.py
lastest -> latest
Former-commit-id: a0a82a56765ffbdc2aeaa8174835494459ac914a
|
2023-07-11 18:03:53 -04:00 |
|
hiyouga
|
8de7a01887
|
fix sft encode
Former-commit-id: 2369a96a3200593421ae9afb06e08e2ac8010bb2
|
2023-07-11 19:50:33 +08:00 |
|
hiyouga
|
cc290a41e6
|
add baichuan template
Former-commit-id: 22273b3f7ce3b4c13e9e3f3677181d1a6a0f9c84
|
2023-07-11 18:57:50 +08:00 |
|
hiyouga
|
bc436066c8
|
update api to match langchain
Former-commit-id: 0016cf6525b151a6e7262967399d67033569b7eb
|
2023-07-07 20:35:39 +08:00 |
|
hiyouga
|
113cdaf1cb
|
support InternLM
Former-commit-id: a454ef7d57d9c06302d51464cfe39f6d0c48c5a8
|
2023-07-07 11:02:28 +08:00 |
|
hiyouga
|
601b1747d1
|
fix rouge score
Former-commit-id: b84b03a2a5ca72ce0ba71d9a9c3db1a687283fa6
|
2023-07-06 14:28:34 +08:00 |
|
hiyouga
|
982e76978b
|
fix streaming response in API
Former-commit-id: 72a17ae3b4fac2dc93b04a816f16f863120bc71b
|
2023-07-05 22:42:31 +08:00 |
|
hiyouga
|
d659907f34
|
fix freeze tuning
Former-commit-id: e32a1db967da02f502559df59ec6d1ab4554febf
|
2023-07-05 21:18:28 +08:00 |
|
hiyouga
|
df71d98b37
|
fix bug in PPO stage
Former-commit-id: a27373128d10b4e483d306100d91a55c0b796488
|
2023-07-05 19:14:10 +08:00 |
|
hiyouga
|
4de9ef568a
|
fix compute dtype
Former-commit-id: 5aadbb22730d19570b039462c91df443dbb34b5f
|
2023-07-05 15:13:00 +08:00 |
|
hiyouga
|
f1de82f08e
|
support falcon model #72
Former-commit-id: 72cc3ff0e6de641073de1159196319705f8efe85
|
2023-07-05 15:00:06 +08:00 |
|
hiyouga
|
4b093996a7
|
fix bleu score
Former-commit-id: 6874dce4444e6e6ce9d6125275dbf3dfdfb4fb22
|
2023-07-05 00:11:21 +08:00 |
|
hiyouga
|
e4e36a2d74
|
set use_cache before saving model
Former-commit-id: a6a0161f32f600f3001188ff4c7929c5f13c2a03
|
2023-07-04 23:18:20 +08:00 |
|
hiyouga
|
6df5c4ccef
|
fix seq2seq predictions
Former-commit-id: 045316d62f713311bdabdfb56be442238e03a007
|
2023-07-04 22:56:51 +08:00 |
|
hiyouga
|
d720f67e6c
|
fix typo
Former-commit-id: 23c0d36abe881d9be839d5c647841bdef178307b
|
2023-06-30 10:09:59 +08:00 |
|
hiyouga
|
6290955e84
|
update loading logic
Former-commit-id: f1da17bb0deeb39a29da4dc208951d1ad69bb8ba
|
2023-06-28 12:07:16 +08:00 |
|
hiyouga
|
6b6430489a
|
fix loading best model
Former-commit-id: cf7db6855d353a57344c78d6b56478ffb14ceff2
|
2023-06-28 01:55:12 +08:00 |
|
hiyouga
|
4ae8a20e1d
|
fix RM accuracy
Former-commit-id: 532a385ea60693fdf835e6bc8e240ff8d55ff3a7
|
2023-06-28 01:40:13 +08:00 |
|
hiyouga
|
e19dcc13e3
|
tiny fix
Former-commit-id: 994f2a79831a1dea8425e3eff62f0bc8238b78d6
|
2023-06-27 23:54:24 +08:00 |
|
hiyouga
|
2d22961c7d
|
fix initializing data arguments
Former-commit-id: e6b83c8b87cb93358086121a6f9ccaba5dfa7497
|
2023-06-27 22:50:23 +08:00 |
|
hiyouga
|
640f774d30
|
support save full model, replace BOS token
Former-commit-id: 32e56c290802ba971c08f471b94a33daec85671a
|
2023-06-27 21:40:11 +08:00 |
|
hiyouga
|
33c2b063c6
|
fix decoding in seq2seq
Former-commit-id: 44227f651bf9a6a4741b3e0845cdb5f2ab58ea63
|
2023-06-27 19:33:08 +08:00 |
|
hiyouga
|
a8f580d753
|
fix generation in seq2seq.py
Former-commit-id: f847d196beb6d04e456d64665a10dc9316a869f2
|
2023-06-26 18:07:06 +08:00 |
|
hiyouga
|
3aa1ca66e0
|
support prefixes, loading multiple local files
Former-commit-id: 6672e09836ed0103693a381ece010377bd0ef4f8
|
2023-06-26 15:32:40 +08:00 |
|
hiyouga
|
83346e86af
|
update api
Former-commit-id: a90db46e336a657d5fcf480986bfc68c77ad416b
|
2023-06-26 13:39:57 +08:00 |
|
hiyouga
|
f9332bc329
|
update readme
Former-commit-id: 6b08adc8219caacefa8d7b5a618e33ccd6060eec
|
2023-06-23 00:17:05 +08:00 |
|
hiyouga
|
7daf6c8b8e
|
update API
Former-commit-id: b5c47b0bef022e90e42406e28b6282492419e3fb
|
2023-06-22 20:46:24 +08:00 |
|
hiyouga
|
391bf1c699
|
match api with OpenAI format
Former-commit-id: 9cbe2b98b024393817e86ff8e3ff1636776fa263
|
2023-06-22 20:27:00 +08:00 |
|
Bun
|
810d9e36ea
|
Compatible with OpenAI API.
Former-commit-id: d21d51377bf7834a019efc009f4543b14c438389
|
2023-06-21 14:45:04 +08:00 |
|
hiyouga
|
de2c418637
|
add default template
Former-commit-id: c64fb6b83fdbedd62073417213f0215207ff1311
|
2023-06-16 21:12:17 +08:00 |
|
hiyouga
|
ee22b80ad0
|
fix freeze layers
Former-commit-id: 8a16359c121d543aeea3650612df46fc1bad1428
|
2023-06-16 17:38:21 +08:00 |
|
hiyouga
|
de9da40b18
|
add source prefix
Former-commit-id: 4f0fe959fcd2dded56a95ff3ad620bd381ae17a6
|
2023-06-16 16:32:17 +08:00 |
|
hiyouga
|
3836aadacf
|
support loading lora from hub
Former-commit-id: 0b34c962bc3368dca62b18ad6c27a0293c3affa5
|
2023-06-16 00:02:17 +08:00 |
|
hiyouga
|
194c5d2bee
|
support baichuan model
Former-commit-id: d683042fbcb2ee43b9823262d0a65b64f4cb54cb
|
2023-06-15 16:02:01 +08:00 |
|
hiyouga
|
496846e819
|
fix bug in template vanilla
Former-commit-id: 9b51e44c95af116aec34e7b6495935420f7c6c27
|
2023-06-15 14:36:55 +08:00 |
|
hiyouga
|
c42562d7ae
|
add BOS token in pre-training
Former-commit-id: c57cf5d4a46c57c6f698e5cfd0fd59cce703094d
|
2023-06-15 01:46:17 +08:00 |
|
hiyouga
|
aa1bb8a9a2
|
support multiturn training like FastChat
Former-commit-id: 629cafb1a09924e82d7ea1f9fba318d3f5593196
|
2023-06-14 22:27:39 +08:00 |
|