Commit Graph

1712 Commits

Author SHA1 Message Date
hiyouga
180fd06e61 fix flash shift short attention
Former-commit-id: 0a356bc897
2023-10-09 17:54:48 +08:00
hiyouga
9c6d34020c fix webui args
Former-commit-id: 6b24f29c8a
2023-10-09 17:13:57 +08:00
hiyouga
b6e81a0307 fix shift short attention
Former-commit-id: ab65c3063b
2023-10-09 17:07:46 +08:00
hiyouga
8de990b1e9 update webui #1086
Former-commit-id: b8dbec086e
2023-10-09 14:50:14 +08:00
hiyouga
3a7bcb585b fix #1097
Former-commit-id: a683c5b797
2023-10-08 22:29:26 +08:00
hiyouga
69c99819d6 add llamafy_qwen.py
Former-commit-id: f9769cff8a
2023-10-08 22:05:36 +08:00
hiyouga
93809d1c3b Update wechat.jpg
Former-commit-id: de5523449e
2023-10-07 12:48:13 +08:00
hiyouga
6bc861c15b Update wechat.jpg
Former-commit-id: 134a65b2fb
2023-10-04 22:03:28 +08:00
hiyouga
d338ab3e19 fix #1068 #1074
Former-commit-id: d11a545463
2023-09-28 14:39:16 +08:00
hiyouga
f88088c43d fix bug in packed sft dataset
Former-commit-id: de19614306
2023-09-28 01:16:46 +08:00
hiyouga
f61a000e73 tiny fix
Former-commit-id: 5d4118b096
2023-09-28 01:03:04 +08:00
hiyouga
8a8ba08bf7 tiny fix
Former-commit-id: d2ebd225db
2023-09-28 01:02:11 +08:00
hiyouga
755e3e49b4 fix #1064
Former-commit-id: c902236397
2023-09-28 00:53:29 +08:00
hiyouga
d2ce9b879b fix bug in pretraining
Former-commit-id: b3fbba57eb
2023-09-28 00:45:20 +08:00
hiyouga
deb17942ab fix layer norm dtype
Former-commit-id: 84b7486885
2023-09-28 00:25:55 +08:00
hiyouga
f66e6b91c7 fix #1026
Former-commit-id: b0b0138e1d
2023-09-27 22:57:09 +08:00
hiyouga
ca6a3bc76f fix #424
Former-commit-id: 35fa94723c
2023-09-27 22:49:43 +08:00
hiyouga
772a1b16a1 fix #1032
Former-commit-id: a41e12de5e
2023-09-27 22:42:16 +08:00
hiyouga
927ff702ff refactor finetuning Args
Former-commit-id: 620efe1d8d
2023-09-27 22:28:06 +08:00
hiyouga
650a2a2e01 update readme
Former-commit-id: 4eae061464
2023-09-27 21:57:47 +08:00
hiyouga
108c31e1fc support LongLoRA
Former-commit-id: 90375f600d
2023-09-27 21:55:50 +08:00
hiyouga
88f2e99c73 add CMMLU, update eval script
Former-commit-id: 4dd9b4d982
2023-09-23 21:10:17 +08:00
hiyouga
02549e3162 update evaluate
Former-commit-id: f8ff625d76
2023-09-23 11:55:31 +08:00
hiyouga
467c30d591 move file
Former-commit-id: badd2735b5
2023-09-23 11:52:12 +08:00
hiyouga
98aa2ef7f5 shuffle few shot examples
Former-commit-id: ef1ea1aead
2023-09-23 00:53:20 +08:00
hiyouga
c714e445d8 fix MMLU
Former-commit-id: 2340b0d7df
2023-09-23 00:42:23 +08:00
hiyouga
5ee1bdecdc add MMLU and C-Eval script
Former-commit-id: 465ee8119a
2023-09-23 00:34:17 +08:00
hiyouga
e930682152 fix #1000
Former-commit-id: 5cc7a44784
2023-09-22 15:00:48 +08:00
hiyouga
db21953bf0 update readme
Former-commit-id: 044d4425b4
2023-09-22 14:34:13 +08:00
hiyouga
ff21424290 fix webui
Former-commit-id: 5f3ab3ddde
2023-09-21 19:55:38 +08:00
hiyouga
3bdc40b4db tiny fix
Former-commit-id: dbaef776a1
2023-09-21 19:52:06 +08:00
hiyouga
4581d09fa6 fix #944
Former-commit-id: 338b8664ed
2023-09-21 19:51:02 +08:00
hiyouga
d04585df59 tiny fix
Former-commit-id: ace3f85a72
2023-09-21 15:25:29 +08:00
hiyouga
2bc685feee Merge branch 'main' of https://github.com/hiyouga/LLaMA-Efficient-Tuning
Former-commit-id: e510006ed6
2023-09-21 13:52:19 +08:00
hiyouga
7aff33a0dc Update wechat.jpg
Former-commit-id: 837b487d8a
2023-09-21 13:52:02 +08:00
hoshi-hiyouga
2e493f8d2a Merge pull request #975 from statelesshz/npu-support
Add Ascend NPU support

Former-commit-id: ac8648b431
2023-09-20 14:56:50 +08:00
statelesshz
95384eefe8 support export model on Ascend NPU
Former-commit-id: b3e41c6d49
2023-09-20 10:26:02 +08:00
hiyouga
d7f267a9f9 fix webui
Former-commit-id: 10ab2f8b90
2023-09-19 18:35:21 +08:00
hiyouga
48e7b600a8 fix error info
Former-commit-id: 7e8655c8b5
2023-09-19 18:30:23 +08:00
hiyouga
4e6e42bb55 add tests.cal_flops.py
Former-commit-id: 469f859161
2023-09-16 23:40:41 +08:00
hiyouga
65854736c3 update readme
Former-commit-id: acda45e463
2023-09-16 17:33:01 +08:00
hiyouga
2a75b10015 fix #913
Former-commit-id: 0b5f970c05
2023-09-15 20:58:28 +08:00
hiyouga
5377d0bf95 fix #896
Former-commit-id: 8632bff811
2023-09-14 18:37:34 +08:00
hiyouga
632fff02e0 fix #887
Former-commit-id: 8857e45602
2023-09-14 17:56:58 +08:00
hoshi-hiyouga
fe2ac71d11 Merge pull request #900 from mmbwf/main
Fix PPO replace_model loading wrong default parameters.

Former-commit-id: 3202985087
2023-09-14 17:34:22 +08:00
hiyouga
550fa84e0d Update wechat.jpg
Former-commit-id: bd4e24bfee
2023-09-14 16:31:11 +08:00
mmbwf
6ded1725d9 Update utils.py
Fix parameters load error.

Former-commit-id: 30fb721f12
2023-09-14 15:38:04 +08:00
hiyouga
1cd0ea1f13 add MathInstruct dataset
Former-commit-id: 026af87e7f
2023-09-13 22:30:14 +08:00
hiyouga
c8780205bc fix ppo save model
Former-commit-id: 7ba57d5b14
2023-09-12 16:25:29 +08:00
hiyouga
4e86462bad fix #762 #814
Former-commit-id: d4be857e23
2023-09-12 16:10:10 +08:00