658 Commits

Author SHA1 Message Date
hiyouga
82592501be support mixtral
Former-commit-id: 75b5b8e36ab1933b2625f11b645f56cbc805fd85
2023-12-12 11:39:04 +08:00
hiyouga
d75327e786 fix baichuan resize
Former-commit-id: 66956d13074a9bc74d7a737b9476f38361a7764a
2023-12-11 20:55:50 +08:00
hiyouga
903cc3dcc1 tiny fix
Former-commit-id: 1f839fc4f278c2a258df22899241fc66a2cca682
2023-12-11 18:09:40 +08:00
hiyouga
51de180a2e support resize embeddings #1786
Former-commit-id: 368a41bd3c6a04f869083058d9165954fbdad105
2023-12-11 17:50:02 +08:00
hiyouga
02b5f23266 use peft 0.7.0, fix #1561 #1764
Former-commit-id: 423947bd58aa50da8785b8ceca1e7e288447a9da
2023-12-11 17:13:40 +08:00
hiyouga
8149cee890 fix #1784
Former-commit-id: 4e1af5a5d39d9e2f374c1372e2d67120c63fea09
2023-12-09 20:53:18 +08:00
yuze.zyz
0cacd5147a fix typo
Former-commit-id: 29b07291e6b40e9f0a61632609465363291ae5c7
2023-12-08 18:13:26 +08:00
yuze.zyz
c2432b2e8d support ms dataset
Former-commit-id: 98638b35dc24045ac17b9b01d08d3a02372acef3
2023-12-08 18:00:57 +08:00
hiyouga
14f7ea1185 fix #1771 and temporarily fix #1764
Former-commit-id: d0e5a5d604e16c2fe0035b0ac1d54dc3625d4da3
2023-12-08 16:26:20 +08:00
hiyouga
ad0069e5a2 add models
Former-commit-id: 758ae7937a41a95016e70180fb343011763c1b67
2023-12-06 13:33:18 +08:00
hiyouga
28ed4cb3f4 fix ppo trainer save logic
Former-commit-id: 5e70c41e4e12a1109570b0ff56346fe212c028ed
2023-12-04 19:00:19 +08:00
hiyouga
7250a6db54 update readme
Former-commit-id: a15f8cf19cac42acfb9917a2d7c9fa36a838b360
2023-12-04 11:22:01 +08:00
hiyouga
b7cdc1d4e9 update readme
Former-commit-id: d3c46cb126a9182be765341fe31c860d71430712
2023-12-04 11:02:29 +08:00
hiyouga
cf70644f8f fix #1715
Former-commit-id: 3f9192dbbbafdc2171d2eb80282d5cae47565b7b
2023-12-03 22:35:47 +08:00
hiyouga
2e4f938b8a release v0.3.3
Former-commit-id: 72ddb5fcce1649599671de214667d8d899ef5203
2023-12-03 21:59:45 +08:00
hiyouga
3c667217be fix bug
Former-commit-id: 2fd7a8fc3134af66193a5e8db8fea35025f82de9
2023-12-03 21:40:40 +08:00
hiyouga
3d200af1d2 ppo support rm server
Former-commit-id: 20b0edf16f5b42cb2c4a795674647afb68cb3a4a
2023-12-03 21:38:51 +08:00
hiyouga
74851e7033 implement rm server #1543
Former-commit-id: 2e5bb6888c86079493456c2ddd525f8c52b9963e
2023-12-03 20:52:54 +08:00
hiyouga
9bf0dcfe39 fix #1707 #1710
Former-commit-id: 243a596518ad69cf1eec20a082534b9e94353ce4
2023-12-03 11:33:12 +08:00
hiyouga
a58d846a29 add logo
Former-commit-id: 597894ad31c186120335252ccc0cc48fcea701b4
2023-12-02 01:31:24 +08:00
hiyouga
823a75ef22 fix #1642
Former-commit-id: 11be28201f688ac21cf94135067d37e9aa7ab0a1
2023-12-02 00:37:53 +08:00
hiyouga
f7cdc0b54c add xuanyuan models
Former-commit-id: 1dfa9de3723550cddf24bbc0739cad6207731212
2023-12-02 00:35:29 +08:00
hiyouga
d46ce88519 fix gptq training
Former-commit-id: bec58e3dc575aa4247e563881a456328ee5ef496
2023-12-02 00:27:15 +08:00
hiyouga
c58714b9b0 tiny fix
Former-commit-id: fd2782a06ba4efa76cacbb49eb76a05de8d8aca6
2023-12-01 23:37:10 +08:00
hiyouga
3f4a397105 fix gptq model inference
Former-commit-id: f7da9a87cb48cacb7d56322817b05d6f471f6508
2023-12-01 23:34:14 +08:00
hiyouga
dc62b998b9 update readme
Former-commit-id: a0a9408e11f6b4cfb39af3f28402353b7cf48fa6
2023-12-01 22:58:29 +08:00
hiyouga
7d758e2232 fix #1703
Former-commit-id: eee2e9abf6df345c5471e8ca7639293543ba720c
2023-12-01 22:55:41 +08:00
hiyouga
caf4fa46e0 patch modelscope
Former-commit-id: 8888cf53f040f5a2d8c0e59cddf79b252449bf58
2023-12-01 22:53:15 +08:00
hoshi-hiyouga
b475323bdb Merge pull request #1700 from tastelikefeet/feat/support_ms
Support ModelScope hub

Former-commit-id: f79c3b663a91ac2a7cdcf71192b6dd84f110b8f1
2023-12-01 20:25:18 +08:00
hoshi-hiyouga
6f3e3174c1 Merge branch 'main' into feat/support_ms
Former-commit-id: b8954342611e24bc3af972747fd016cde89eee3f
2023-12-01 20:23:46 +08:00
yuze.zyz
9d84f0af29 remove useless code
Former-commit-id: 323df46dd6a8eaf1fd608380406dcbce80c097b2
2023-12-01 17:28:23 +08:00
tastelikefeet
bf2b6e11b1 fix bug
Former-commit-id: 6d483e76141420e0cb577541e6e1794c20f025f6
2023-12-01 17:27:00 +08:00
hiyouga
2cd9adee01 fix err hint
Former-commit-id: 935a4a01bd9204129dd72a500ed75b268714d1e8
2023-12-01 17:13:22 +08:00
hiyouga
f106969943 add err hint
Former-commit-id: 2cf0249ec6f7524c39a6c8df73593f6d25b665b7
2023-12-01 17:04:37 +08:00
hoshi-hiyouga
ceae52b0a0 Merge pull request #1699 from Samge0/patch-1
Update .gitignore

Former-commit-id: ab9da1bc5043fedeac8e57614e5986ebdd2128af
2023-12-01 16:52:57 +08:00
SamgeShao
1f1fd98ce6 Update .gitignore
Former-commit-id: b2ec86ef63683665382c2fda142c3d9743e3c8a7
2023-12-01 16:37:41 +08:00
yuze.zyz
b8ee512ec2 add readme
Former-commit-id: 3d5ec6f12b4ae7d04520e6865516a9a6dd4f7efe
2023-12-01 16:11:30 +08:00
hiyouga
eec19b9693 tiny fix
Former-commit-id: 37aa7099dff2a9a7b52e259dac92de41ce606946
2023-12-01 15:58:50 +08:00
hoshi-hiyouga
264103aceb Merge pull request #1695 from Samge0/dev
Improve:"CUDA_VISIBLE_DEVICES" read from the env

Former-commit-id: b49cde0c29774820dcf4463e3f1ef00114af7219
2023-12-01 15:56:18 +08:00
hoshi-hiyouga
48db7fd3e9 Merge pull request #1690 from billvsme/main
Improve get_current_device

Former-commit-id: c3b8cc27c91248a7381b3333abf099064412dc1a
2023-12-01 15:44:35 +08:00
hiyouga
1602fe2350 fix #1696
Former-commit-id: 722ae14a652af34d9b91f9459e613d7959ecaa7e
2023-12-01 15:34:50 +08:00
tastelikefeet
b880f45705 add model
Former-commit-id: 48e8d8438bc6cd2c75dc39419c45aaebb34a2e0a
2023-12-01 15:06:17 +08:00
hoshi-hiyouga
634da9ee68 Merge pull request #1689 from mlinmg/patch-2
Update dataset_info.json - Added Nectar

Former-commit-id: 50b029fa981576e4be1a7a08b62f9e0109c085e0
2023-12-01 14:29:36 +08:00
samge
eda1acb191 Improve:"CUDA_VISIBLE_DEVICES" read from the env
Former-commit-id: 7a61daa8be76779c876d685c57c464133ca70752
2023-12-01 11:35:02 +08:00
Marco
238379e64a Update dataset_info.json
Added the Nectar dataset already preprocessed and divided in sft and rl to which I added a preprompt to each instruction since it has been seen that this increase instruction following

Former-commit-id: 6336e247c1535f356194046607038245bc48464f
2023-11-30 16:21:34 +01:00
billvsme
bd907d8dce improve get_current_device
Former-commit-id: 2b07815e7fc8dc6ad0a7e9eccdd6681fbab35f3c
2023-11-30 22:40:35 +08:00
hiyouga
24dd0db807 fix #1597
Former-commit-id: d77a3a79a0e854803a57af8ac6a7246691f69f70
2023-11-30 21:47:06 +08:00
hiyouga
ca70d8393d fix #1668
Former-commit-id: bccc71259e703ca1e1d88169e385a026c4efa92e
2023-11-30 21:02:00 +08:00
hiyouga
4f3699efd2 fix #1682
Former-commit-id: 06d56696731eadbeeea615eae4efce1b6c36def4
2023-11-30 20:03:32 +08:00
hiyouga
46066ed801 add models
Former-commit-id: b9eaadde8b5f4b9f89fa7bb910b325fcf9c84434
2023-11-30 19:16:13 +08:00