Commit Graph

  • 11b55a3270 fix webui hiyouga 2023-10-22 17:24:56 +08:00
  • f793ca0a2c add new options in webui hiyouga 2023-10-22 17:17:58 +08:00
  • b79ca8781e fix recursion error hiyouga 2023-10-22 16:28:37 +08:00
  • 7b4acf7265 reimplement neftune hiyouga 2023-10-22 16:15:08 +08:00
  • b42a145253 Merge pull request #1252 from anvie/neftune hoshi-hiyouga 2023-10-22 15:59:20 +08:00
  • 57fb40aa04 add NEFTune optimization anvie 2023-10-21 13:24:10 +07:00
  • 8fdff07e1f fix openchat template hiyouga 2023-10-21 01:25:42 +08:00
  • 641ffa2f6e fix tokenizer padding side in evaluate.py hiyouga 2023-10-21 00:30:04 +08:00
  • b665e9e133 fix #1232 hiyouga 2023-10-20 23:28:52 +08:00
  • 0fcf66049d fix #1215 hiyouga 2023-10-19 16:19:21 +08:00
  • 7a11a42dfd fix #1218 hiyouga 2023-10-19 16:17:41 +08:00
  • cb0edd2302 fix #1228 hiyouga 2023-10-19 15:54:10 +08:00
  • 6496a99b7d fix #1217 hiyouga 2023-10-19 15:52:24 +08:00
  • 1611fad6bc rename webui hiyouga 2023-10-16 15:16:24 +08:00
  • 85480f2e86 fix #1197 hiyouga 2023-10-16 15:13:46 +08:00
  • 5f83a6e72c Update README_zh.md hoshi-hiyouga 2023-10-16 00:28:27 +08:00
  • beacb798ea Update README.md hoshi-hiyouga 2023-10-16 00:23:37 +08:00
  • 7a53188048 release v0.2.0 hiyouga 2023-10-15 20:49:43 +08:00
  • f5d0da4d2a update readme hiyouga 2023-10-15 20:28:14 +08:00
  • 25d326e135 Update README.md hoshi-hiyouga 2023-10-15 20:23:22 +08:00
  • a6a04be2e6 fix config, #1191 hiyouga 2023-10-15 18:28:45 +08:00
  • 0d63584c03 disable tqdm in webui mode hiyouga 2023-10-15 16:18:25 +08:00
  • ea82f8a82a refactor export, fix #1190 hiyouga 2023-10-15 16:01:48 +08:00
  • 273745f9b9 fix eval resuming in webui hiyouga 2023-10-15 15:45:38 +08:00
  • 3ad8c92eca tiny fix hiyouga 2023-10-15 05:02:48 +08:00
  • 1e9401744c fix callback hiyouga 2023-10-15 04:59:44 +08:00
  • a63a1cebb2 Merge pull request #1186 from hiyouga/dev hoshi-hiyouga 2023-10-15 04:53:14 +08:00
  • accde3cd39 implement webui resuming training hiyouga 2023-10-15 04:52:19 +08:00
  • fde05cacfc fix bugs in webui hiyouga 2023-10-15 03:41:58 +08:00
  • 7ed1fa6fe9 refactor webui hiyouga 2023-10-15 03:06:21 +08:00
  • c874e764b8 fix loading dtype hiyouga 2023-10-14 20:15:24 +08:00
  • 01d8cb1ca7 fix #1176 #1177 hiyouga 2023-10-14 20:00:17 +08:00
  • af18b0dce7 fix #1184 hiyouga 2023-10-14 19:20:11 +08:00
  • b240b6792f fix webui hiyouga 2023-10-13 16:27:59 +08:00
  • cb42676694 update readme hiyouga 2023-10-13 13:53:43 +08:00
  • c4102f306a update discord link hiyouga 2023-10-12 21:44:28 +08:00
  • 197c754d73 rename repository hiyouga 2023-10-12 21:42:29 +08:00
  • 932e3fee3a Update wechat.jpg hiyouga 2023-10-12 20:45:58 +08:00
  • 11bd271364 fix ppo args hiyouga 2023-10-11 23:40:50 +08:00
  • 2818af0b09 refactor model_dtype, fix PPO trainer hiyouga 2023-10-11 23:16:01 +08:00
  • 5310e4d182 add averaging in evaluation hiyouga 2023-10-10 23:16:31 +08:00
  • be420e4179 fix aquila template, repair sft packing mechanism hiyouga 2023-10-10 18:49:55 +08:00
  • e1dcb8e4dc tiny fix hiyouga 2023-10-10 17:41:13 +08:00
  • 8e2ed6b8ce update readme hiyouga 2023-10-09 20:02:50 +08:00
  • 0a356bc897 fix flash shift short attention hiyouga 2023-10-09 17:54:48 +08:00
  • 6b24f29c8a fix webui args hiyouga 2023-10-09 17:13:57 +08:00
  • ab65c3063b fix shift short attention hiyouga 2023-10-09 17:07:46 +08:00
  • b8dbec086e update webui #1086 hiyouga 2023-10-09 14:50:14 +08:00
  • a683c5b797 fix #1097 hiyouga 2023-10-08 22:29:26 +08:00
  • f9769cff8a add llamafy_qwen.py hiyouga 2023-10-08 22:05:36 +08:00
  • de5523449e Update wechat.jpg hiyouga 2023-10-07 12:48:13 +08:00
  • 134a65b2fb Update wechat.jpg hiyouga 2023-10-04 22:03:28 +08:00
  • d11a545463 fix #1068 #1074 hiyouga 2023-09-28 14:39:16 +08:00
  • de19614306 fix bug in packed sft dataset hiyouga 2023-09-28 01:16:46 +08:00
  • 5d4118b096 tiny fix hiyouga 2023-09-28 01:03:04 +08:00
  • d2ebd225db tiny fix hiyouga 2023-09-28 01:02:11 +08:00
  • c902236397 fix #1064 hiyouga 2023-09-28 00:53:29 +08:00
  • b3fbba57eb fix bug in pretraining hiyouga 2023-09-28 00:45:20 +08:00
  • 84b7486885 fix layer norm dtype hiyouga 2023-09-28 00:25:55 +08:00
  • b0b0138e1d fix #1026 hiyouga 2023-09-27 22:57:09 +08:00
  • 35fa94723c fix #424 hiyouga 2023-09-27 22:49:43 +08:00
  • a41e12de5e fix #1032 hiyouga 2023-09-27 22:42:16 +08:00
  • 620efe1d8d refactor finetuning Args hiyouga 2023-09-27 22:28:06 +08:00
  • 4eae061464 update readme hiyouga 2023-09-27 21:57:47 +08:00
  • 90375f600d support LongLoRA hiyouga 2023-09-27 21:55:50 +08:00
  • 4dd9b4d982 add CMMLU, update eval script hiyouga 2023-09-23 21:10:17 +08:00
  • f8ff625d76 update evaluate hiyouga 2023-09-23 11:55:31 +08:00
  • badd2735b5 move file hiyouga 2023-09-23 11:52:12 +08:00
  • ef1ea1aead shuffle few shot examples hiyouga 2023-09-23 00:53:20 +08:00
  • 2340b0d7df fix MMLU hiyouga 2023-09-23 00:42:23 +08:00
  • 465ee8119a add MMLU and C-Eval script hiyouga 2023-09-23 00:34:17 +08:00
  • 5cc7a44784 fix #1000 hiyouga 2023-09-22 15:00:48 +08:00
  • 044d4425b4 update readme hiyouga 2023-09-22 14:34:13 +08:00
  • 5f3ab3ddde fix webui hiyouga 2023-09-21 19:55:38 +08:00
  • dbaef776a1 tiny fix hiyouga 2023-09-21 19:52:06 +08:00
  • 338b8664ed fix #944 hiyouga 2023-09-21 19:51:02 +08:00
  • ace3f85a72 tiny fix hiyouga 2023-09-21 15:25:29 +08:00
  • e510006ed6 Merge branch 'main' of https://github.com/hiyouga/LLaMA-Efficient-Tuning hiyouga 2023-09-21 13:52:19 +08:00
  • 837b487d8a Update wechat.jpg hiyouga 2023-09-21 13:52:02 +08:00
  • ac8648b431 Merge pull request #975 from statelesshz/npu-support hoshi-hiyouga 2023-09-20 14:56:50 +08:00
  • b3e41c6d49 support export model on Ascend NPU statelesshz 2023-09-20 10:15:59 +08:00
  • 10ab2f8b90 fix webui hiyouga 2023-09-19 18:35:21 +08:00
  • 7e8655c8b5 fix error info hiyouga 2023-09-19 18:30:23 +08:00
  • 469f859161 add tests.cal_flops.py hiyouga 2023-09-16 23:40:41 +08:00
  • acda45e463 update readme hiyouga 2023-09-16 17:33:01 +08:00
  • 0b5f970c05 fix #913 hiyouga 2023-09-15 20:58:28 +08:00
  • 8632bff811 fix #896 hiyouga 2023-09-14 18:37:34 +08:00
  • 8857e45602 fix #887 hiyouga 2023-09-14 17:56:58 +08:00
  • 3202985087 Merge pull request #900 from mmbwf/main hoshi-hiyouga 2023-09-14 17:34:22 +08:00
  • bd4e24bfee Update wechat.jpg hiyouga 2023-09-14 16:31:11 +08:00
  • 30fb721f12 Update utils.py mmbwf 2023-09-14 15:38:04 +08:00
  • 026af87e7f add MathInstruct dataset hiyouga 2023-09-13 22:30:14 +08:00
  • 7ba57d5b14 fix ppo save model hiyouga 2023-09-12 16:25:29 +08:00
  • d4be857e23 fix #762 #814 hiyouga 2023-09-12 16:10:10 +08:00
  • 3b306478d4 tiny fix hiyouga 2023-09-11 18:27:08 +08:00
  • ccb3553576 Release v0.1.8 hiyouga 2023-09-11 17:31:34 +08:00
  • 0fbece85a7 update flashattn, fix ppo save model hiyouga 2023-09-11 17:25:36 +08:00
  • b218c271ed remove PeftTrainer hiyouga 2023-09-10 22:23:23 +08:00
  • baac22f4f4 truncate readme hiyouga 2023-09-10 21:04:20 +08:00
  • 63611de7ae update readme hiyouga 2023-09-10 21:01:20 +08:00