812 Commits

Author SHA1 Message Date
hiyouga
7443ac3116 fix chat engine, update webui
Former-commit-id: 5d956e2a5167201aecdfce2794c25d8a2d84e234
2024-03-08 03:01:53 +08:00
hiyouga
2235020cc9 update galore args
Former-commit-id: 0ac6b40a4772b61a3476bb74b976d24c408a2c35
2024-03-08 01:17:32 +08:00
hiyouga
5b50458acf fix galore
Former-commit-id: 33a4c24a8a3c153bc62edf74b9246699a0ae3233
2024-03-08 00:44:51 +08:00
hiyouga
f373290012 add Yi-9B model
Former-commit-id: 57452a4aa1d37a047d659f002c1aaa6246f64178
2024-03-07 23:11:57 +08:00
hiyouga
2c010c72b8 support galore
Former-commit-id: 28f78621883917425fabe49f5473778111012127
2024-03-07 22:41:36 +08:00
hiyouga
34533b2f35 support vllm
Former-commit-id: d07ad5cc1cdbc13879afd84f653afdfee03a6933
2024-03-07 20:26:31 +08:00
hiyouga
37e40563f1 fix #2735
Former-commit-id: f74f804a715dfb16bf24a056bc95db6b102f9ed7
2024-03-07 16:15:53 +08:00
hoshi-hiyouga
90e66c8d94 Merge pull request #2730 from cx2333-gt/main
fix flash_attn in train_web

Former-commit-id: 2185855bdb7d4cb55f3af796e35fb1b0e8dce5e3
2024-03-07 14:37:18 +08:00
cx2333
013c12a135 revert choice name
Former-commit-id: 94b7a1b91588716e9e91f7aae7126ed924e55953
2024-03-07 14:28:55 +08:00
hiyouga
843d3f7a97 fix chatglm3 template
Former-commit-id: 921ee822679bd10fcc14d084d0845e6132e570dd
2024-03-07 14:26:16 +08:00
cx2333
22624e566e fix flash_attn in train_web
Former-commit-id: a8889498fa4e9b6c7a82422ed5b1da3662b48d42
2024-03-07 10:13:55 +08:00
hiyouga
31c618f1f7 tiny fix
Former-commit-id: 0048a2021e94d068f7c6054df0b9569ae4912eb1
2024-03-06 17:25:08 +08:00
hiyouga
8b6c178249 export use balanced gpu
Former-commit-id: 3e84f430b14a94e68f5815d8e412f0d74d28a04c
2024-03-06 16:33:14 +08:00
hiyouga
8b21a60d9c fix add tokens
Former-commit-id: 9658c63cd94d28bba730a19f73397580b9865d6b
2024-03-06 15:04:02 +08:00
hiyouga
e887aface7 fix version checking
Former-commit-id: 3016e6565708637c1d760f2cd5a67cbd8a5a6c26
2024-03-06 14:51:51 +08:00
hiyouga
af526c3a46 fix arg dtype
Former-commit-id: e0c47358f9d09ab64acbb5ebafc61b52b5b1f2af
2024-03-05 20:53:30 +08:00
hiyouga
9561809ce9 improve aqlm optim
Former-commit-id: 259af60d28985b919911587716c24a3ac7f7de64
2024-03-05 20:49:50 +08:00
hiyouga
c776cdfc3e optimize aqlm training
Former-commit-id: d3d3dac7070eb9055bcdc91eaf53f5b3741c0bda
2024-03-05 18:35:41 +08:00
hiyouga
0f2250b831 fix dora inference
Former-commit-id: ddf352f861e04e813cb8adeb4513964b4945081a
2024-03-05 11:51:41 +08:00
hiyouga
768358b960 fix export model
Former-commit-id: e5edcf440f2c96b90b1186ada887873f19d3c152
2024-03-05 11:05:41 +08:00
hiyouga
eeb34e5696 auto set chat template
Former-commit-id: 9e56eaf2d3e42d3985b0e68929a3a32e1db157ef
2024-03-05 02:41:20 +08:00
hiyouga
b04316d9a8 update readme
Former-commit-id: 24a79bd50f972008ca1a862edaff7cdd6c211cef
2024-03-04 19:29:26 +08:00
hiyouga
a62d17d009 fix export on cpu device
Former-commit-id: cda2ff87272797a062c7addb1bf840ac46208dfd
2024-03-04 17:35:09 +08:00
hiyouga
0e58cd6422 fix sub-process error in thread
Former-commit-id: 9c10854b46fc67d45ff9fc2f62af4d6af826f9c1
2024-03-03 15:04:35 +08:00
hiyouga
9ae1514a75 update readme, add starcoder2, cosmopedia
Former-commit-id: 894d183214417b10af64d6add7be082d63e8b1f3
2024-03-03 01:01:46 +08:00
hiyouga
d1e6e02461 fix #2649
Former-commit-id: 4e5fae2fac85227641bd16159cf296a32e0b18b4
2024-03-01 13:02:41 +08:00
hiyouga
82f26bc959 tiny fix
Former-commit-id: 396fd4794735f2315e75cfe82b095591d58bb021
2024-02-29 21:03:48 +08:00
hiyouga
72f7ec38db fix webui
Former-commit-id: 1bfa70ce8eca408fb15e63fd60422aa7b7233d12
2024-02-29 20:09:09 +08:00
hiyouga
3787d13816 fix #2642
Former-commit-id: c0be617195f43d972681dd59727857b1247eeb7e
2024-02-29 18:32:54 +08:00
hiyouga
1853b5c172 tiny fix
Former-commit-id: 4a871e80e205466262534cdc710b0495954b153e
2024-02-29 17:28:50 +08:00
hiyouga
8487b66532 tiny fix and release
Former-commit-id: ece3b3737e7b07895b556a7cc02dd841a2d84e8e
2024-02-29 00:46:47 +08:00
hoshi-hiyouga
d2b8645b60 Merge pull request #2575 from lungothrin/feature/chatter-with-role
support on fly test of tools

Former-commit-id: 7c87532476ab9dc0f25a4e79181bd0a3f4f05855
2024-02-29 00:39:47 +08:00
hiyouga
60ceace8a0 fix #2629
Former-commit-id: 4cc2781efebd696ca42ce3c71d80e2eb707040cf
2024-02-29 00:37:29 +08:00
hiyouga
8e7d50dae4 release v0.5.3
Former-commit-id: fa5ab21ebc0ab738178c0c57578db3bda995ae06
2024-02-29 00:34:19 +08:00
hiyouga
57f85add58 update chatglm3 template
Former-commit-id: 38d8b2cef8d70ce8c390de0317559df7f04b4a5d
2024-02-28 21:11:23 +08:00
hiyouga
5abbca70d3 support DoRA, AWQ, AQLM #2512
Former-commit-id: cfefacaa37453a15c55866d019887f24e886a577
2024-02-28 19:53:28 +08:00
Liang Ge
8d7fcd64b5 support on fly test of tools
Former-commit-id: 56b3918fdab5a20847ebc40cc02639158c4c1a44
2024-02-28 01:17:49 +08:00
hiyouga
3af5fea981 update readme
Former-commit-id: 3ba10545937cd9a1dea9cf65d98dd174a205337d
2024-02-26 17:25:47 +08:00
Rayrtfr
41e9dd2cf8 Support Atom Model
Former-commit-id: 6e0fba60b3857c8920edb6bd2a34a7f2d4ac46be
2024-02-26 10:44:10 +08:00
hiyouga
62efecee77 update webui
Former-commit-id: 2e592be53624c243d003586ec414baf678d04cfd
2024-02-25 20:23:41 +08:00
hoshi-hiyouga
db53b67fe4 Merge pull request #2525 from stephen-nju/main
update project_kwargs for ppo config

Former-commit-id: 4aab19c7ef160b18eac5c6aea5e648cabd2db72c
2024-02-25 15:54:00 +08:00
hiyouga
279ba19ef7 fix data entry
Former-commit-id: 354f13c01a31d468c214cd35acf614433392e96a
2024-02-23 18:29:24 +08:00
hiyouga
223633556b fix gemma template
Former-commit-id: 6bf4c1274f4e9c91a6b37bd4c420c2369eaae65a
2024-02-23 13:49:53 +08:00
hiyouga
9f22befe4c fix template
Former-commit-id: a87838ded1245b00016e7568635ed7146eadb207
2024-02-22 12:09:21 +08:00
hiyouga
e1246cc507 fix template
Former-commit-id: c375a20230cfad3f398dfa0a1140d5b071fca687
2024-02-22 12:06:48 +08:00
hiyouga
1845e03921 support gemma
Former-commit-id: c99e19641a9b893da0a3277bd41bd1d3996d1913
2024-02-21 23:27:36 +08:00
hiyouga
2f738a1db6 fix #2532
Former-commit-id: 3cc10a01a792a92b99b952a45bb21c25097fccf6
2024-02-21 21:55:14 +08:00
hiyouga
ec42d2c385 tiny fix
Former-commit-id: daa318535097a51bdb8546960a9e4b4681c11dfe
2024-02-21 18:30:29 +08:00
stephen
1b4d54b873 update project_kwargs for ppo config
Former-commit-id: 42c23798f27977af777587ded7f4845010f0184a
2024-02-21 13:47:38 +08:00
hiyouga
0fcb931f18 support lora for llama pro
Former-commit-id: 9aeb404a946795d6c4fa3cb45e3e96ffeec13646
2024-02-21 02:17:22 +08:00