142 Commits

Author SHA1 Message Date
hiyouga
9b13d04127 create chat model
Former-commit-id: bddf583b2fc099c957a1037418bd8504a837663e
2023-07-15 19:26:20 +08:00
hiyouga
6d4a107546 Update callbacks.py
Former-commit-id: 44ebe58083dc62128fd14df474c11c6e09af43db
2023-07-15 17:39:16 +08:00
hiyouga
75a97a3991 fix callback
Former-commit-id: 065680cd2a410d7ceab10a4a76588df43e286117
2023-07-15 17:18:16 +08:00
hiyouga
a69b1b1c3a modity code structure
Former-commit-id: 0682ed357210897e0b67c4a6eb31a94b3eb929f1
2023-07-15 16:54:28 +08:00
hiyouga
6bead216e9 fix eval and pred loss
Former-commit-id: 2a5a8e0eba279de603c2d25e894b6d2921aaae55
2023-07-14 13:11:57 +08:00
hiyouga
fd956c218b fix pretrain
Former-commit-id: 75b584875fc75c437491a5155ef310248e9b9dd4
2023-07-13 23:41:54 +08:00
hiyouga
25182c4779 fix Baichuan-13B
Former-commit-id: 6d9d826b3246349454c68f4d13b862da4de986e2
2023-07-13 23:08:45 +08:00
Jinghuan Shang
c0078c755f Fix typo in common.py
lastest -> latest

Former-commit-id: a0a82a56765ffbdc2aeaa8174835494459ac914a
2023-07-11 18:03:53 -04:00
hiyouga
102f4f425c fix sft encode
Former-commit-id: 2369a96a3200593421ae9afb06e08e2ac8010bb2
2023-07-11 19:50:33 +08:00
hiyouga
eadd531543 add baichuan template
Former-commit-id: 22273b3f7ce3b4c13e9e3f3677181d1a6a0f9c84
2023-07-11 18:57:50 +08:00
hiyouga
7a90e44b03 update api to match langchain
Former-commit-id: 0016cf6525b151a6e7262967399d67033569b7eb
2023-07-07 20:35:39 +08:00
hiyouga
60108653a9 support InternLM
Former-commit-id: a454ef7d57d9c06302d51464cfe39f6d0c48c5a8
2023-07-07 11:02:28 +08:00
hiyouga
642dab8081 fix rouge score
Former-commit-id: b84b03a2a5ca72ce0ba71d9a9c3db1a687283fa6
2023-07-06 14:28:34 +08:00
hiyouga
83bc87e73f fix streaming response in API
Former-commit-id: 72a17ae3b4fac2dc93b04a816f16f863120bc71b
2023-07-05 22:42:31 +08:00
hiyouga
82cbbc0e48 fix freeze tuning
Former-commit-id: e32a1db967da02f502559df59ec6d1ab4554febf
2023-07-05 21:18:28 +08:00
hiyouga
837c27525c fix bug in PPO stage
Former-commit-id: a27373128d10b4e483d306100d91a55c0b796488
2023-07-05 19:14:10 +08:00
hiyouga
2e75897fc1 fix compute dtype
Former-commit-id: 5aadbb22730d19570b039462c91df443dbb34b5f
2023-07-05 15:13:00 +08:00
hiyouga
6b5a085ddf support falcon model #72
Former-commit-id: 72cc3ff0e6de641073de1159196319705f8efe85
2023-07-05 15:00:06 +08:00
hiyouga
195099e5df fix bleu score
Former-commit-id: 6874dce4444e6e6ce9d6125275dbf3dfdfb4fb22
2023-07-05 00:11:21 +08:00
hiyouga
7e8e0c320b set use_cache before saving model
Former-commit-id: a6a0161f32f600f3001188ff4c7929c5f13c2a03
2023-07-04 23:18:20 +08:00
hiyouga
a2e7d88473 fix seq2seq predictions
Former-commit-id: 045316d62f713311bdabdfb56be442238e03a007
2023-07-04 22:56:51 +08:00
hiyouga
1c24c80a6b fix typo
Former-commit-id: 23c0d36abe881d9be839d5c647841bdef178307b
2023-06-30 10:09:59 +08:00
hiyouga
11f8c31101 update loading logic
Former-commit-id: f1da17bb0deeb39a29da4dc208951d1ad69bb8ba
2023-06-28 12:07:16 +08:00
hiyouga
72d2656c04 fix loading best model
Former-commit-id: cf7db6855d353a57344c78d6b56478ffb14ceff2
2023-06-28 01:55:12 +08:00
hiyouga
7ba498d142 fix RM accuracy
Former-commit-id: 532a385ea60693fdf835e6bc8e240ff8d55ff3a7
2023-06-28 01:40:13 +08:00
hiyouga
d21a64160d tiny fix
Former-commit-id: 994f2a79831a1dea8425e3eff62f0bc8238b78d6
2023-06-27 23:54:24 +08:00
hiyouga
4f2c204f13 fix initializing data arguments
Former-commit-id: e6b83c8b87cb93358086121a6f9ccaba5dfa7497
2023-06-27 22:50:23 +08:00
hiyouga
9342c6411b support save full model, replace BOS token
Former-commit-id: 32e56c290802ba971c08f471b94a33daec85671a
2023-06-27 21:40:11 +08:00
hiyouga
f5efc01531 fix decoding in seq2seq
Former-commit-id: 44227f651bf9a6a4741b3e0845cdb5f2ab58ea63
2023-06-27 19:33:08 +08:00
hiyouga
f2dc451141 fix generation in seq2seq.py
Former-commit-id: f847d196beb6d04e456d64665a10dc9316a869f2
2023-06-26 18:07:06 +08:00
hiyouga
b6968a6940 support prefixes, loading multiple local files
Former-commit-id: 6672e09836ed0103693a381ece010377bd0ef4f8
2023-06-26 15:32:40 +08:00
hiyouga
d97da03cd5 update api
Former-commit-id: a90db46e336a657d5fcf480986bfc68c77ad416b
2023-06-26 13:39:57 +08:00
hiyouga
a9e6753f4e update readme
Former-commit-id: 6b08adc8219caacefa8d7b5a618e33ccd6060eec
2023-06-23 00:17:05 +08:00
hiyouga
3d08e8c7fb update API
Former-commit-id: b5c47b0bef022e90e42406e28b6282492419e3fb
2023-06-22 20:46:24 +08:00
hiyouga
bfe015e30f match api with OpenAI format
Former-commit-id: 9cbe2b98b024393817e86ff8e3ff1636776fa263
2023-06-22 20:27:00 +08:00
Bun
13fabdcc96 Compatible with OpenAI API.
Former-commit-id: d21d51377bf7834a019efc009f4543b14c438389
2023-06-21 14:45:04 +08:00
hiyouga
b9e225bc20 add default template
Former-commit-id: c64fb6b83fdbedd62073417213f0215207ff1311
2023-06-16 21:12:17 +08:00
hiyouga
3db9b51f04 fix freeze layers
Former-commit-id: 8a16359c121d543aeea3650612df46fc1bad1428
2023-06-16 17:38:21 +08:00
hiyouga
e4ab754adc add source prefix
Former-commit-id: 4f0fe959fcd2dded56a95ff3ad620bd381ae17a6
2023-06-16 16:32:17 +08:00
hiyouga
6d1e733311 support loading lora from hub
Former-commit-id: 0b34c962bc3368dca62b18ad6c27a0293c3affa5
2023-06-16 00:02:17 +08:00
hiyouga
fa2c840610 support baichuan model
Former-commit-id: d683042fbcb2ee43b9823262d0a65b64f4cb54cb
2023-06-15 16:02:01 +08:00
hiyouga
6907d1900d fix bug in template vanilla
Former-commit-id: 9b51e44c95af116aec34e7b6495935420f7c6c27
2023-06-15 14:36:55 +08:00
hiyouga
11df2ab717 add BOS token in pre-training
Former-commit-id: c57cf5d4a46c57c6f698e5cfd0fd59cce703094d
2023-06-15 01:46:17 +08:00
hiyouga
11bace2e93 support multiturn training like FastChat
Former-commit-id: 629cafb1a09924e82d7ea1f9fba318d3f5593196
2023-06-14 22:27:39 +08:00
hiyouga
febe41a481 fix loading valuehead
Former-commit-id: 7872375d7a0c1d8826206631f6717a91ec49f1b3
2023-06-13 11:13:06 +08:00
hiyouga
fdfc22196c fix generating args
Former-commit-id: 52805a8441bd7b324bd89489de60f18f103c8e4c
2023-06-13 01:33:56 +08:00
hiyouga
0da1b7d9ab support RM metrics, add generating Args
Former-commit-id: c461c6190bc124e98dde7f3cf96a59ce40b26fb0
2023-06-12 15:48:48 +08:00
BUAADreamer
a976cba730 add code for reading from multi files in one directory
Former-commit-id: 9b80cf08b9f0d4aee896b228fb76399e9a7c9d8b
2023-06-10 16:27:30 +08:00
BUAADreamer
2012cb5cbc add code for reading from multi files in one directory
Former-commit-id: b7ebb83a96619e5111b0faa9da9d0feb8d9cdff0
2023-06-10 15:53:47 +08:00
hiyouga
6978c1625a tiny fix
Former-commit-id: c9c795f9c7cd2228410a12af4ec10d3b59be87db
2023-06-07 16:42:31 +08:00