Commit Graph

Select branches

Hide Pull Requests

main

Mono Color

• 34005252df update readme hiyouga 2023-09-10 20:52:21 +08:00
• d8aa1404be support FlashAttention2 hiyouga 2023-09-10 20:43:56 +08:00
• 815b92e698 fix #850 hiyouga 2023-09-10 14:22:03 +08:00
• a51b7c98ac fix lora target hiyouga 2023-09-09 17:04:45 +08:00
• bca1a247bc support lora target auto find hiyouga 2023-09-09 15:38:37 +08:00
• d8d82ca281 fix chatglm2 tokenizer hiyouga 2023-09-09 13:50:29 +08:00
• d2015c8e12 add baichuan2 convert script hiyouga 2023-09-08 22:59:41 +08:00
• 90bd085ae4 fix bug in DPO data collator hiyouga 2023-09-08 20:45:07 +08:00
• b34797a845 fix #761 hiyouga 2023-09-08 20:22:18 +08:00
• 8ea32e4046 change to right-padding, update reward score #803 hiyouga 2023-09-08 20:04:31 +08:00
• 8aaaa132d4 fix chatglm template hiyouga 2023-09-08 14:45:58 +08:00
• 8b66247d2f Update wechat.jpg hiyouga 2023-09-07 20:56:07 +08:00
• f5351c18e1 update requirements hiyouga 2023-09-07 19:26:25 +08:00
• 5a9970dbef fix #818 hiyouga 2023-09-07 19:19:53 +08:00
• ed1c2c5557 add deepspeed check in PPO training hiyouga 2023-09-07 19:12:40 +08:00
• e2bf7c3bad fix #809 hiyouga 2023-09-07 19:04:32 +08:00
• 85b1f6632a fix baichuan templates hiyouga 2023-09-07 18:54:14 +08:00
• 0531886e1f update baichuan2 template hiyouga 2023-09-06 21:43:06 +08:00
• 60603a94c6 add Baichuan2 models hiyouga 2023-09-06 18:40:11 +08:00
• 62ce65c628 add Baichuan2 models hiyouga 2023-09-06 18:36:04 +08:00
• 9224db90ea Merge pull request #786 from kinghuin/patch-1 hoshi-hiyouga 2023-09-05 10:49:34 +08:00
• a19fc2ebf7 fix utils.py bug Q 2023-09-05 10:38:01 +08:00
• 370bdb6e43 fix #763 hiyouga 2023-09-01 23:13:05 +08:00
• a9d1fb72f7 refactor dataset_attr, add eos in pt, fix #757 hiyouga 2023-09-01 19:00:45 +08:00
• cf106e9d65 Update wechat.jpg hiyouga 2023-09-01 15:02:23 +08:00
• 701a9d60cb Merge pull request #741 from hiyouga/feature-addDatasetCheck codingma 2023-08-31 20:57:36 +08:00
• 0bcc489c42 update llama2 template codemayq 2023-08-30 16:23:56 +08:00
• f7fdc088d4 add dataset stage check codemayq 2023-08-30 16:23:08 +08:00
• 9b4d16d040 Merge pull request #651 from hiyouga/feature-dataset_stage codingma 2023-08-28 16:03:45 +08:00
• 01dfba85b4 Merge pull request #678 from hiyouga/feature-txt_preview codingma 2023-08-28 16:03:02 +08:00
• 604f85487b add ad gen dataset codemayq 2023-08-27 20:35:32 +08:00
• 15cec650c7 Update wechat.jpg hiyouga 2023-08-27 01:21:31 +08:00
• 24e68d29f2 add text format dataset preview in webui codemayq 2023-08-24 19:45:36 +08:00
• ba94c8729d add stage in DatasetAttr codemayq 2023-08-23 20:54:53 +08:00
• 2de1a7610a fix import error hiyouga 2023-08-23 20:45:03 +08:00
• 57146c101f fix #649 hiyouga 2023-08-23 20:21:15 +08:00
• cece66d48a add readme for dataset codemayq 2023-08-23 19:55:45 +08:00
• c0e4d1e81b add dataset stage and filter dataset when stage chosen in webui codemayq 2023-08-23 18:54:23 +08:00
• 1c702ad538 fix webui hiyouga 2023-08-23 11:03:35 +08:00
• c562307476 Merge pull request #644 from hiyouga/fix-quantization_bit hoshi-hiyouga 2023-08-23 10:45:45 +08:00
• a7cc6c4140 fix quantization bit is "" codemayq 2023-08-23 10:08:17 +08:00
• ec2047b064 fix quantization is "" codemayq 2023-08-23 10:04:03 +08:00
• 4318347d3f update template hiyouga 2023-08-22 19:46:09 +08:00
• 4da719c830 Merge pull request #629 from panpan0000/main hoshi-hiyouga 2023-08-22 13:41:44 +08:00
• b0ca8fe634 add rm dataset explanation Peter Pan 2023-08-22 01:30:57 -04:00
• bc7795655f Merge pull request #619 from hiyouga/feature-templateTest hoshi-hiyouga 2023-08-21 20:56:34 +08:00
• cbbee7933e add template encode test codemayq 2023-08-21 20:51:24 +08:00
• 5235b15c91 fix #617 hiyouga 2023-08-21 18:16:11 +08:00
• 02d69b6fde fix #608 hiyouga 2023-08-21 17:49:36 +08:00
• 0a3f698425 fix baichuan template for training #597 #616 hiyouga 2023-08-21 17:41:51 +08:00
• 5c052836a0 fix #595 hiyouga 2023-08-20 16:40:00 +08:00
• 1968d9d1d0 Merge pull request #596 from beat4ocean/beat hoshi-hiyouga 2023-08-20 16:37:40 +08:00
• 7b45de6b9f fix KeyError: 'lang' bug beat4ocean 2023-08-20 15:32:36 +08:00
• 0676497104 fix ppo trainer #551 hiyouga 2023-08-20 14:07:11 +08:00
• 290be836b7 Update wechat.jpg hiyouga 2023-08-19 18:03:36 +08:00
• 9c9009f49f Release v0.1.7 hiyouga 2023-08-18 17:21:27 +08:00
• d75e377b0f tiny fix hiyouga 2023-08-18 13:07:35 +08:00
• 53e33418d0 support ppo score norm (trl 0.5.1.dev required) hiyouga 2023-08-18 12:02:42 +08:00
• 9020524418 fix PPO trainer #551 , update readme hiyouga 2023-08-18 11:43:10 +08:00
• e4eec9ddfd update readme hiyouga 2023-08-18 01:51:55 +08:00
• 10cd6c9171 Update .gitignore hiyouga 2023-08-18 01:43:42 +08:00
• 58f13e22da update training resuming hiyouga 2023-08-18 01:41:17 +08:00
• 7926432d27 Merge pull request #434 from niuba/main hoshi-hiyouga 2023-08-18 01:38:31 +08:00
• 7252903245 Merge branch 'main' into main hoshi-hiyouga 2023-08-18 01:37:23 +08:00
• d125218cde support bf16 ppo #551 hiyouga 2023-08-18 00:40:32 +08:00
• 9f4c2adc9a fix ChatGLM2 ppo #527 #528 hiyouga 2023-08-18 00:34:59 +08:00
• be21fc83f9 fix generation bug #532 hiyouga 2023-08-17 22:21:34 +08:00
• b0ed0dec5e fix streaming in pt stage #548 #549 hiyouga 2023-08-17 17:59:26 +08:00
• ff0aa793b6 update readme hiyouga 2023-08-17 11:00:22 +08:00
• 892fd39373 fix baichuan and intern template hiyouga 2023-08-17 01:27:20 +08:00
• d9e62711a3 fix generation hiyouga 2023-08-16 22:39:54 +08:00
• 7407d9daa1 fix system prompt hiyouga 2023-08-16 01:35:52 +08:00
• 273135f595 fix baichuan template #481 hiyouga 2023-08-15 11:38:21 +08:00
• 7f35487c4a Merge pull request #516 from liuyanyi/add_gitignore hoshi-hiyouga 2023-08-15 11:25:40 +08:00
• af6c011fcb fix ChatGLM RLHF hiyouga 2023-08-15 11:19:20 +08:00
• a7dd9611db Update wechat.jpg hiyouga 2023-08-15 11:13:46 +08:00
• 448478f938 Add .gitignore Yanyi Liu 2023-08-15 11:13:45 +08:00
• 80b4053602 alert pad_token source hiyouga 2023-08-15 00:07:56 +08:00
• 9d0f6214b6 update webui hiyouga 2023-08-14 22:45:26 +08:00
• adb0f186e9 Merge pull request #511 from hiyouga/feature-autoTemplate hoshi-hiyouga 2023-08-14 22:44:04 +08:00
• 0bf892ff1a auto match template when change model_name codemayq 2023-08-14 20:56:05 +08:00
• 79c68e5527 add template match and stage in webui codemayq 2023-08-14 20:42:59 +08:00
• d019956808 fix ChatGLM lm_head #494 hiyouga 2023-08-14 14:14:48 +08:00
• 20a29297b1 fix bug in webui hiyouga 2023-08-14 11:38:42 +08:00
• ca08e5efd3 fix webui cache hiyouga 2023-08-14 11:37:01 +08:00
• 2391a84e26 update readme_zh hiyouga 2023-08-14 11:13:25 +08:00
• ec94274ca1 web UI integrating RLHF hiyouga 2023-08-14 10:48:47 +08:00
• 2f2fd55d81 fix #480 hiyouga 2023-08-14 00:23:56 +08:00
• d69b1388e6 fix webui hiyouga 2023-08-12 23:52:07 +08:00
• 9dc6a296e3 tiny fix hiyouga 2023-08-12 22:02:43 +08:00
• 8545c11c45 fix rope scaling hiyouga 2023-08-12 22:00:01 +08:00
• 8a79ded55d update readme hiyouga 2023-08-12 21:29:06 +08:00
• 3ea1fa35d1 update readme hiyouga 2023-08-12 21:25:19 +08:00
• 2618e0b5a7 update readme hiyouga 2023-08-12 21:23:05 +08:00
• 1836c020c5 update readme hiyouga 2023-08-12 21:00:11 +08:00
• fa940c17b8 support rope scaling, fix #475 #476 #478 hiyouga 2023-08-12 20:46:27 +08:00
• 2eb0eca65f Merge pull request #479 from hiyouga/feature-addCmdExport hoshi-hiyouga 2023-08-12 20:41:52 +08:00
• 6bc8e9866d add sft script preview in webui codemayq 2023-08-12 13:53:55 +08:00
• dd51c24203 fix unusual output of 8bit models #278 #391 hiyouga 2023-08-12 00:25:29 +08:00
• a48cb0d474 Release v0.1.6 hiyouga 2023-08-11 23:25:57 +08:00