610 Commits

Author SHA1 Message Date
yuze.zyz
c523613f0a support ms dataset
Former-commit-id: 9c2247d700763f480d88a5dd46480cb32cfc174e
2023-12-08 18:00:57 +08:00
hoshi-hiyouga
9a26819a58 Merge branch 'main' into feat/support_ms
Former-commit-id: 00f5c9ee1608b98ab8f40bcafdc3edc71833257f
2023-12-01 20:23:46 +08:00
yuze.zyz
fcd61657ee remove useless code
Former-commit-id: 5a2392f105704810e9ce96c13fcc8a555726f9b8
2023-12-01 17:28:23 +08:00
tastelikefeet
eb835b693d fix bug
Former-commit-id: d9e52957e272e8133f1b37cf20d193084425e09e
2023-12-01 17:27:00 +08:00
hiyouga
e964fa7df7 fix err hint
Former-commit-id: a5a248d569f8bf97cb9be71221783d97c666583c
2023-12-01 17:13:22 +08:00
hiyouga
dbb8342ec0 add err hint
Former-commit-id: a51b8ec620e52cbfcad91d12f0acd7c73f448444
2023-12-01 17:04:37 +08:00
hoshi-hiyouga
947192900a Merge pull request #1699 from Samge0/patch-1
Update .gitignore

Former-commit-id: aec946b119ed46346236d7958e24a0dcb0c44a4d
2023-12-01 16:52:57 +08:00
SamgeShao
c5842fcd96 Update .gitignore
Former-commit-id: 7cabb9903dd3830ead03c786e494d51cc09a3b66
2023-12-01 16:37:41 +08:00
yuze.zyz
b2200409f5 add readme
Former-commit-id: 5aa6751e52b5c2e06727c50e60218226b146b7bf
2023-12-01 16:11:30 +08:00
hiyouga
a44ba7a2b8 tiny fix
Former-commit-id: e597d3c084c8700e247bad6e26d2ee40fc3c316b
2023-12-01 15:58:50 +08:00
hoshi-hiyouga
6e094e491e Merge pull request #1695 from Samge0/dev
Improve:"CUDA_VISIBLE_DEVICES" read from the env

Former-commit-id: fbc6220692ba3a20c749eeda1d8c3abe1a037537
2023-12-01 15:56:18 +08:00
hoshi-hiyouga
752b3dd58d Merge pull request #1690 from billvsme/main
Improve get_current_device

Former-commit-id: d043a4e7ba2457679eeca8de5820a4f07b7d8401
2023-12-01 15:44:35 +08:00
hiyouga
9a6b694e12 fix #1696
Former-commit-id: bf6f6aeefe65b4949633648b8711525c0029c001
2023-12-01 15:34:50 +08:00
tastelikefeet
63e12226a0 add model
Former-commit-id: 8ce4d11e38518b0b4657c7e64394d471cbb0bd6d
2023-12-01 15:06:17 +08:00
hoshi-hiyouga
43ff245d88 Merge pull request #1689 from mlinmg/patch-2
Update dataset_info.json - Added Nectar

Former-commit-id: a0fde6e421f8cf2355ba041efdbfb4e14e67a418
2023-12-01 14:29:36 +08:00
samge
7cf4e3b9c6 Improve:"CUDA_VISIBLE_DEVICES" read from the env
Former-commit-id: 421d4de604493e1e26ec8348dab3eae138f46b86
2023-12-01 11:35:02 +08:00
Marco
a26f68ba47 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: 9468ee9012bfe7124fc5cc2acebcfe03a6d0cdee
2023-11-30 16:21:34 +01:00
billvsme
e400f2e8ad improve get_current_device
Former-commit-id: 40dfcbc3d4571ce022b6aa39db581c8b88a75b8d
2023-11-30 22:40:35 +08:00
hiyouga
3d291a82d3 fix #1597
Former-commit-id: 327d7f7efe1fefe4bf4646c07fc4917a42c13383
2023-11-30 21:47:06 +08:00
hiyouga
ba6d290d0b fix #1668
Former-commit-id: 1585962eb7ed042890d4c56422aae749c669dda8
2023-11-30 21:02:00 +08:00
hiyouga
bb6b4823ad fix #1682
Former-commit-id: a38dbf55e32a18838eea7f254fd9022fe33bca08
2023-11-30 20:03:32 +08:00
hiyouga
1c43fb6a41 add models
Former-commit-id: 509abe8864ada29ac7fa0f636b662531c8dd3a33
2023-11-30 19:16:13 +08:00
yuze.zyz
45925e4a9c fix
Former-commit-id: fb2204c183ae8c061ed6ec7f4f1bfbb0b4900c9b
2023-11-29 21:43:58 +08:00
yuze.zyz
e08e0e5814 support ms
Former-commit-id: d38a2e7341100902b6c761895b1fe6191c905d06
2023-11-29 20:36:55 +08:00
hiyouga
8ec3617f19 add gpu requirement #1657
Former-commit-id: 9d38e5687d6edd692a33f10729450e8d9e0ab0bf
2023-11-29 12:05:03 +08:00
hiyouga
ecfc7d1b50 fix #1658
Former-commit-id: 77d1b14fc2d9703d15bbd879f67df037db9fbb28
2023-11-28 20:57:24 +08:00
hiyouga
ae1048db6d fix #1659
Former-commit-id: 475a3fa0f4c09d4cfd55ec66271a6d3c9eb5f4d2
2023-11-28 20:52:28 +08:00
hiyouga
33dc25e24f Update wechat.jpg
Former-commit-id: c2d4300ac489e1ec0817adde8e4e754162b72394
2023-11-28 17:27:23 +08:00
hiyouga
b015ac35d8 support export size setting
Former-commit-id: 859a6ea9425a09d7263f6436d05102df8129c248
2023-11-26 18:34:09 +08:00
hiyouga
5f2943dc84 support Yi-34B-Chat models
Former-commit-id: ff1c289229ee382d3e76578bbb6a5e299b969ded
2023-11-23 19:31:49 +08:00
hiyouga
c4f6cf1270 update readme
Former-commit-id: 5085b00a1d84a5a83c857c2716313d4ea84ba424
v0.3.2
2023-11-21 13:15:46 +08:00
hiyouga
9697c3e970 set version
Former-commit-id: 35c2da3eba064e16b21c20a4cde3355173d5d9fd
2023-11-20 22:57:44 +08:00
hiyouga
4966bd7911 support GPTQ tuning #729 #1481 #1545 , fix chatglm template #1453 #1480 #1569
Former-commit-id: 9ea93801459b0d271d21a2d730c44abae9106c51
2023-11-20 22:52:11 +08:00
hiyouga
f06c4c8f7a update ppo trainer
Former-commit-id: 5021062493ed63ad1f6133cfb543e4e7f528d2cc
2023-11-20 21:39:15 +08:00
hoshi-hiyouga
d72f123851 Merge pull request #1553 from hannlp/hans
Change the default argument settings for PPO training

Former-commit-id: 48211e3799a16de946360930d3d92f5a40e9d12d
2023-11-20 20:32:55 +08:00
hiyouga
a7b1632ace fix value head model resuming
Former-commit-id: 2a36fd5064f028f394ac07c25440fd5e965a07b8
2023-11-20 19:01:37 +08:00
hiyouga
682d81caa9 fix #1567
Former-commit-id: 99a3f06377d2886c4000ce7e3583b12ca965534d
2023-11-20 18:46:36 +08:00
hiyouga
32545bd6d9 better data streaming
Former-commit-id: 00baaa990e099d6b75436eaa7a922a07646afa26
2023-11-19 23:32:47 +08:00
hiyouga
d1e03512f4 fix model card network issue
Former-commit-id: 211b2db5a8290f6b52f0a076de56fcc2b06671d6
2023-11-19 23:03:19 +08:00
hiyouga
8d82d7e994 fix Mistral template
https://github.com/lm-sys/FastChat/pull/2547

Former-commit-id: bfb94331657f385f4653ddcb8f7b57d1c052804d
2023-11-19 16:29:30 +08:00
hiyouga
a53afb27eb fix #1263
Former-commit-id: 065bfaeed490a4e03fb48a5adc0b8af4d835a767
2023-11-19 16:05:18 +08:00
hiyouga
48d6d925f7 fix #1558
Former-commit-id: 1740131d63d32aefc0370441baf4716ddb5ebcfe
2023-11-19 14:15:47 +08:00
hiyouga
112108d564 fix evaluator and cached_file in 4.31.0
Former-commit-id: ff6056405dea8e89a95fd3741fd309d3c7679896
2023-11-18 19:39:23 +08:00
hiyouga
6d8d8509da update benchmark
Former-commit-id: a2019c8b61753e0a845dc2b3d3b45ae43c0d492f
2023-11-18 11:30:01 +08:00
hiyouga
60fe410f05 update readme
Former-commit-id: 90212280d6cc168e5421fd3201a69d2c6ae01e29
2023-11-18 11:15:56 +08:00
hiyouga
3dc7c0a88c add benchmark
Former-commit-id: 329134f58c45746702ec92a5bd76b89334cbc4b6
2023-11-18 11:09:52 +08:00
hiyouga
303956cbb9 update dataset
Former-commit-id: 7b1aa6f63c79c0d9cb5249fdb0d6a5f9a04f36bd
2023-11-17 23:19:12 +08:00
hiyouga
0d98d1a28c fix quantization
Former-commit-id: ccb0f58e22f55b15531fd0e85f5935b150575bec
2023-11-17 22:21:29 +08:00
hiyouga
f9df6c17ed fix #1550
Former-commit-id: 1bbc1be95eedf0796c0b311568dff8c75f87dfbb
2023-11-17 17:23:13 +08:00
Yuchen Han
b92259ae02 Update README_zh.md
Former-commit-id: 7cab47b822ddf7f94d2ccfbe2ba4836e35f104f4
2023-11-17 00:18:07 -08:00