1743 Commits

Author SHA1 Message Date
hiyouga
56a6db6d84 fix ppo dataset bug #4012
Former-commit-id: 7fc51b2e93698ae5e012566af8481f4d861c873d
2024-06-06 19:03:20 +08:00
hiyouga
67246f52f2 update trainers
Former-commit-id: b7f6c4a171293cf4f3e88f15a811f847342f84ee
2024-06-06 18:45:49 +08:00
hiyouga
e963a470c1 fix base64 image read #4061
Former-commit-id: 66ccb2a27a04296b4600f2c85f428071bf14eeb0
2024-06-06 17:29:19 +08:00
hiyouga
a4e1fcc881 update readme
Former-commit-id: cc331fa2d28afe081937c50ea83d63add21d4e3a
2024-06-06 16:59:18 +08:00
hiyouga
ed8dc92e39 update readme
Former-commit-id: fb1f709af5199976e63d7188e088e33c75d19bfe
2024-06-06 16:25:42 +08:00
hiyouga
990dd6d44c lora modules: all by default
Former-commit-id: 52c4ae87c7f4312704c31ef26b079b2c5b95ea5f
2024-06-06 03:53:28 +08:00
hiyouga
8d9f3022d2 add codestral 22B
Former-commit-id: b011c7f527a57cb1d21c4e2c9631c2fb62bb835e
2024-06-06 03:42:50 +08:00
hiyouga
e9f9b1f250 lint
Former-commit-id: 9030501eaef97ea249347198272adf0d709503ec
2024-06-06 03:33:44 +08:00
hoshi-hiyouga
fbc1168294 Merge pull request #4066 from injet-zhou/main
add throughput entry to training log

Former-commit-id: d2816f343f405f3fab09f2a8eade774b886e8f92
2024-06-06 03:32:04 +08:00
hoshi-hiyouga
dd5e377b8e Merge pull request #4080 from MengqingCao/npu
Add npu option for model exporting

Former-commit-id: 07fc67193ef6bcb8e8a392aff0c57a2eb36832bf
2024-06-06 03:15:44 +08:00
hoshi-hiyouga
f002409e6a Update export.py
Former-commit-id: 694833c1104d13929d4f181f014a121f25955dc5
2024-06-06 03:14:46 +08:00
hoshi-hiyouga
79a39ca703 Update model_args.py
Former-commit-id: 09c0afd94a8a5f5b45a61b32c983d50e1b9e2941
2024-06-06 03:14:23 +08:00
hoshi-hiyouga
2c1951f00e Merge pull request #4053 from hzhaoy/feature/add_select_config_file
Support selecting saved configuration files

Former-commit-id: 568ef3cf2a793f268cbe01c39dec418a13e61ecd
2024-06-06 03:06:03 +08:00
hiyouga
c955a332d7 add vllm_dtype arg #3387 #3717
Former-commit-id: a0dd3a6351bb78541d40fec1d2fc457d803c86a4
2024-06-06 02:53:27 +08:00
hiyouga
c91655e952 support train from scratch #4033 #4075
Former-commit-id: 1290b9d01077e62f8de7a23637daa2586cc82bfa
2024-06-06 02:43:19 +08:00
hiyouga
7226fe780d support image input in api #3971 #4061
Former-commit-id: c70aaf763ef22fb83ce3635e8ffd5ec4c89c1cb0
2024-06-06 02:29:55 +08:00
hiyouga
0b671615d0 update train hparams
Former-commit-id: 1ca9fce55b55bf209f4b76152b586731932a3f39
2024-06-06 01:49:20 +08:00
hiyouga
eff00a8172 fix setup
Former-commit-id: b2b80d434fcc0c3838d229098e1c21d26632204c
2024-06-06 01:39:02 +08:00
hiyouga
1935f4a1e0 add llamafactory-cli env
Former-commit-id: 1df077184845ff5f394b9324d46f8c382869e590
2024-06-06 01:28:14 +08:00
hiyouga
fc053cf81f fix #4090
Former-commit-id: d9f15f30a8f4bc64778a5c96baeb6801700d7a2c
2024-06-06 00:50:32 +08:00
MengqingCao
80897e3d6f modify export_device option
Former-commit-id: b2fc4a5499e21a5b9622c2285402efef6e27a74d
2024-06-05 09:37:36 +00:00
hiyouga
861d93a06a fix #4079
Former-commit-id: fda732d7f4616373844c97beff416880260f49db
2024-06-05 16:56:54 +08:00
hiyouga
3d2b081331 update readme
Former-commit-id: 02d34db29a7a35c25711d49e98fd3167a2f4dfe7
2024-06-05 16:32:32 +08:00
MengqingCao
48b2d0d12b fix #4077
Former-commit-id: fedbe92f3b56294acc6c49f9a51e369cf2de3ead
2024-06-05 08:03:30 +00:00
hiyouga
04a7065830 support glm-4
Former-commit-id: a10f4718fbf3f3c89dc7eb31cb8e1a46ca6adda5
2024-06-05 15:16:38 +08:00
MengqingCao
d11ede9dc2 add npu for model export
Former-commit-id: ce020b6eb3f35c1db37ee4835e694eddcd0f59b0
2024-06-05 07:06:40 +00:00
faddddeout
f4cf31a1a0 add throughput entry to log
Former-commit-id: 691f999f64c7bac78761e4354f89816d2f0d46fc
2024-06-04 11:04:29 +00:00
hzhaoy
1ca6d03bc1 add: support selecting saved configuration files and loading training parameters
Former-commit-id: 5c9b17c1dc9093da0ea813642bce9b5c9ae96274
2024-06-04 10:33:43 +08:00
hiyouga
1cc9508fb3 tiny fix
Former-commit-id: f9d50501aac1f60a3b445ca3fee9aa60995461ee
2024-06-04 00:31:10 +08:00
hiyouga
0e81997792 fix #3873
Former-commit-id: 1ac325b4d682bb493573c18bb0b67ceae8d0d372
2024-06-04 00:21:50 +08:00
hiyouga
920b091581 fix #3992
Former-commit-id: a48321fbf5196b88a11106cf74a74fbcea2ea50b
2024-06-04 00:17:36 +08:00
hiyouga
2e87a54bf1 fix abort in webui DDP mode
Former-commit-id: b90ac72d753b13a3eed9cb8b898fac2f2fe5153f
2024-06-04 00:10:24 +08:00
hoshi-hiyouga
b49c5418fc Merge pull request #3987 from injet-zhou/main
Fix cann't interrupt training when using multi GPUs in webui

Former-commit-id: 455bb158b0e600723d2afaa2070b71178f2f5188
2024-06-04 00:04:07 +08:00
hiyouga
f1fe357ee2 fix #4043
Former-commit-id: 67af68f4fc5232760c57b3a0ae780628da09db6a
2024-06-03 23:30:37 +08:00
hiyouga
2dc5743fba remove gc warnings in DPO&KTO
Former-commit-id: b649bdcbafb464a638387429b770fe258b41f8af
2024-06-03 22:53:54 +08:00
hoshi-hiyouga
6cca5c3a41 Merge pull request #4045 from enji-zhou/feature/add_kto
fix KTO Trainer Sampler

Former-commit-id: 8e235beb9cf4939c06ccb753b047326a9839e77f
2024-06-03 22:09:25 +08:00
hoshi-hiyouga
ca60eca259 Update trainer.py
Former-commit-id: 8565d4b43db905374c328ae57c71fc226980d14f
2024-06-03 22:08:38 +08:00
enji.zhou
59aca304c0 fix KTO Trainer Sampler
Former-commit-id: 39eb1bfa272011554322e9bb2534f83b68282a70
2024-06-03 21:32:38 +08:00
hoshi-hiyouga
669e842c97 Merge pull request #4006 from Uminosachi/scheduler-kwargs
Set scheduler_specific_kwargs to get_scheduler

Former-commit-id: c6ed1955fd8990ddb960750913c9d8b13fe0ace3
2024-06-03 19:27:53 +08:00
hiyouga
ba16749942 update placeholder in issue template
Former-commit-id: 5503a90d7e38273b67129e0b9eb62bd1fd23154f
2024-06-03 19:24:10 +08:00
hoshi-hiyouga
58109a3807 Merge pull request #4011 from statelesshz/issue-template
Update bug-report.yml

Former-commit-id: 1fbc46f45ae4e673f0b20b5eacab3d81d1053807
2024-06-03 19:20:43 +08:00
hiyouga
1ef396362b fix #4005 #4013
Former-commit-id: 8608fa268cde5cddf8d0c6c2eb2cb5fa246c1831
2024-06-03 19:12:29 +08:00
hoshi-hiyouga
c8576fe266 Merge pull request #4007 from xu-song/patch-3
Update model_args.py

Former-commit-id: d88b3a0f2707bcc964f642d348295b99f7c796f8
2024-06-03 18:54:37 +08:00
hiyouga
d8d02e65a1 fix #4022
Former-commit-id: 9541f2f1f1b7d7877eb734f051048e52003a3430
2024-06-03 18:38:36 +08:00
hiyouga
ee80c3acf1 bump versions
transformers 4.37.2->4.41.2
datasets 2.14.3->2.16.0
accelerate 0.27.2->0.30.1
peft 0.10.0->0.11.1
trl 0.8.1->0.8.6


Former-commit-id: 5f1e041f7295bf42a41dd4d9e7f0c42fcc37fed2
2024-06-03 18:29:38 +08:00
hiyouga
2e843a4cf6 fix data loader hint
Former-commit-id: 25b56126a11591b0155e2f72b673dd8f45a6c8c9
2024-06-03 18:28:27 +08:00
ylfeng
7226a1b431 remove empty line
Former-commit-id: 3164710971a6d6545629f5bf133f98de5ff0991a
2024-05-31 21:43:08 +08:00
ylfeng
cc62c22559 fix eos
Former-commit-id: 6e236c952958cbfe50b5dcb7b8eff6aea8477922
2024-05-31 21:40:41 +08:00
ylfeng
3f849f2314 supervised packing with greedy knapsack algorithm
Former-commit-id: 24d12396c9aabd49da0b08719068f24679111cc6
2024-05-31 15:33:54 +08:00
Xu Song
0fba220d5d Update model_args.py
Former-commit-id: f1e018587e5722e41962abd60f74043a3e55f692
2024-05-31 14:35:48 +08:00