428 Commits

Author SHA1 Message Date
hiyouga
e49f7f1afe fix bug in packed sft dataset
Former-commit-id: 51d26b2af6612e65a91c576da5270028da27b322
2023-09-28 01:16:46 +08:00
hiyouga
21a454fa6c tiny fix
Former-commit-id: 35b355b76d2a8f8adf3750a905224e52d03d218f
2023-09-28 01:03:04 +08:00
hiyouga
22c6c27f78 tiny fix
Former-commit-id: 7451b2ae7e58d0f1857f01a037672a8c53b1bd0d
2023-09-28 01:02:11 +08:00
hiyouga
aecbb43096 fix #1064
Former-commit-id: fd4660aa72d981d7efdad465f24a59358626c975
2023-09-28 00:53:29 +08:00
hiyouga
fa53fd2db2 fix bug in pretraining
Former-commit-id: 18a2d90bd6e7c3e1e3513e6f9d895e4048b35b04
2023-09-28 00:45:20 +08:00
hiyouga
1c150995ae fix layer norm dtype
Former-commit-id: 67af21961b68d9b54d07b09e444c7140869f26da
2023-09-28 00:25:55 +08:00
hiyouga
6c5d8f089e fix #1026
Former-commit-id: d0940d0dbd03d4bbcc955304566b0d5507edf9e6
2023-09-27 22:57:09 +08:00
hiyouga
dd623325e8 fix #424
Former-commit-id: daaf89f1126112a73b9f115b0f5617a8cd974a3e
2023-09-27 22:49:43 +08:00
hiyouga
e8a375c8f2 fix #1032
Former-commit-id: 1235b2da5a79ffefd1342054ea8e7dabf47398c1
2023-09-27 22:42:16 +08:00
hiyouga
386d85ae72 refactor finetuning Args
Former-commit-id: be425a70a4c8f051717cf1e4464dbd79dae4c0b5
2023-09-27 22:28:06 +08:00
hiyouga
ebb3901b05 update readme
Former-commit-id: badbc210435d92cea8799bcd1af4c738da902cd7
2023-09-27 21:57:47 +08:00
hiyouga
20130b486c support LongLoRA
Former-commit-id: 0832ed37e7947d699f17375648a52f80752c2b6b
2023-09-27 21:55:50 +08:00
hiyouga
73c48d0463 add CMMLU, update eval script
Former-commit-id: 47f31f06a946eefa5a972e4a566cf3ce05e1e111
2023-09-23 21:10:17 +08:00
hiyouga
f7cecd20e3 update evaluate
Former-commit-id: 288137a76ed1528faa39b467da22f6468ba368ee
2023-09-23 11:55:31 +08:00
hiyouga
2bc64a7636 move file
Former-commit-id: 8711ca9b5421f971ee4cb2fada23832f1021577c
2023-09-23 11:52:12 +08:00
hiyouga
9564ddbb48 shuffle few shot examples
Former-commit-id: 2c9c14c122382e640dfa41a3799628c764c99457
2023-09-23 00:53:20 +08:00
hiyouga
28062c71b5 fix MMLU
Former-commit-id: eeab92323899694010469451b8dfb1f00d685bff
2023-09-23 00:42:23 +08:00
hiyouga
35d1921081 add MMLU and C-Eval script
Former-commit-id: 3403f876127b4b99c5e3edb2834cc3b9a3a0063f
2023-09-23 00:34:17 +08:00
hiyouga
4fbdf18c70 fix #1000
Former-commit-id: 85de2d0a99e4a81fae890a963ccbb5c6142d52d4
2023-09-22 15:00:48 +08:00
hiyouga
5e07ab01f0 update readme
Former-commit-id: 776f9ea3a5837cb3f80ebe53f19e9951400bf05d
2023-09-22 14:34:13 +08:00
hiyouga
fac465a21e fix webui
Former-commit-id: e28485b476816c1bd6c34f7ff9efaa9e3fb85176
2023-09-21 19:55:38 +08:00
hiyouga
e145a2ce0c tiny fix
Former-commit-id: d24ea58c1a44b94227f4cb60f13fc1dd79997d01
2023-09-21 19:52:06 +08:00
hiyouga
dc68c313ee fix #944
Former-commit-id: 032245647848aaa4167086636b6c985268c5fee3
2023-09-21 19:51:02 +08:00
hiyouga
95c0d9ab24 tiny fix
Former-commit-id: 1a7ddd8c1d20dc251f53923bd0ab9f3f1031dd21
2023-09-21 15:25:29 +08:00
hoshi-hiyouga
46a718f339 Merge pull request #975 from statelesshz/npu-support
Add Ascend NPU support

Former-commit-id: b348c7569c0d3f46b03fb274226444ac7a80e68d
2023-09-20 14:56:50 +08:00
statelesshz
496ba46960 support export model on Ascend NPU
Former-commit-id: 50f94e6d9d62c848db7a3db85fa999d67ddd9f04
2023-09-20 10:26:02 +08:00
hiyouga
43ae0aca1d fix webui
Former-commit-id: 2aa06a5a74d98ec25ed6e1e39df11230670f5bad
2023-09-19 18:35:21 +08:00
hiyouga
b8574c1b82 fix error info
Former-commit-id: b90ed220c5e94086d2b73045eff2440ff1b58c5c
2023-09-19 18:30:23 +08:00
hiyouga
32f8b1082b add tests.cal_flops.py
Former-commit-id: 47a119db6c6e937f6ed96f70e3cda6031b9fbd0d
2023-09-16 23:40:41 +08:00
hiyouga
6443fef31a update readme
Former-commit-id: 813c2df5dc179d82c6c999f63c2640e7c3f6aaff
2023-09-16 17:33:01 +08:00
hiyouga
14c3795a7d fix #913
Former-commit-id: d67c11d69277292648dd9889a7321345e2c0c437
2023-09-15 20:58:28 +08:00
hiyouga
3d9e2de573 fix #896
Former-commit-id: 4b70d623d817460de4732749110622e4a1b51958
2023-09-14 18:37:34 +08:00
hiyouga
0ca36a0f8d fix #887
Former-commit-id: e131bc03e05ccae3c6ad8bb42ccf2cdcc2cf3cea
2023-09-14 17:56:58 +08:00
mmbwf
3e5555502a Update utils.py
Fix parameters load error.

Former-commit-id: 112850364c7fdb53e3a38d42861404fc519108ce
2023-09-14 15:38:04 +08:00
hiyouga
fbf5b5e0a9 add MathInstruct dataset
Former-commit-id: 3d1d4b47055739854cf9788a902607e1bbba3723
2023-09-13 22:30:14 +08:00
hiyouga
3305e66f8c fix ppo save model
Former-commit-id: 300ca6d904524f46cb520056e1319a1e9a13d169
2023-09-12 16:25:29 +08:00
hiyouga
e19a44c12b fix #762 #814
Former-commit-id: 9a30ee5009040afbc524dbac0dad99904b2adf5f
2023-09-12 16:10:10 +08:00
hiyouga
8b0e6b9d1b tiny fix
Former-commit-id: d8ea0691f84c971e6860526714fc9873c350b064
2023-09-11 18:27:08 +08:00
hiyouga
f3e638ac6a Release v0.1.8
Former-commit-id: d9666411375964d334d0a93ec162b27e05f70d49
v0.1.8
2023-09-11 17:31:34 +08:00
hiyouga
42e0b30476 update flashattn, fix ppo save model
Former-commit-id: 0b08bc3dac246d4aa3f89afb7172529dcad9c39f
2023-09-11 17:25:36 +08:00
hiyouga
a09a7b650d remove PeftTrainer
Former-commit-id: cc0cff3e991f194732d278e627648e528118a719
2023-09-10 22:23:23 +08:00
hiyouga
332d7bbd56 truncate readme
Former-commit-id: fed5d0cc87e4a5a023f2edae622f2820bded1509
2023-09-10 21:04:20 +08:00
hiyouga
d3b6fece71 update readme
Former-commit-id: c42fe77fec2918fe8811d48ec88e9a7c1e6f07ab
2023-09-10 21:01:20 +08:00
hiyouga
9d963b82de update readme
Former-commit-id: b4109cfe548e091cd20fa84815dce5ff3974a090
2023-09-10 20:52:21 +08:00
hiyouga
a402161631 support FlashAttention2
Former-commit-id: 23e56c5554b948d4f08ad87849b261eafd2c7890
2023-09-10 20:43:56 +08:00
hiyouga
b481ad58e6 fix #850
Former-commit-id: e5975c4c6b8bd47ec506b0d4a4703bee05495436
2023-09-10 14:22:03 +08:00
hiyouga
f91c5f2638 fix lora target
Former-commit-id: d822e41e7ac7e310ee49e347fc45754284ce30b8
2023-09-09 17:04:45 +08:00
hiyouga
7143c551ab support lora target auto find
Former-commit-id: bce9984733d88bf013847eed523d1c75fdf0995e
2023-09-09 15:38:37 +08:00
hiyouga
50e93392dd fix chatglm2 tokenizer
Former-commit-id: 1ab60b4a93fa1be5dfe6ffbd4deb64c0f9d9b431
2023-09-09 13:50:29 +08:00
hiyouga
9f83e93839 add baichuan2 convert script
Former-commit-id: 4d676e0ea9e59c1be13ecb47734917ba78938ac8
2023-09-08 22:59:41 +08:00