Commit Graph

  • 10d59e9e4a make dataset script BUAADreamer 2024-04-25 21:32:01 +08:00
  • 058ed5e607 modify style BUAADreamer 2024-04-25 21:29:50 +08:00
  • 110c2ce2a5 modify style BUAADreamer 2024-04-25 21:27:48 +08:00
  • c425436676 modify style BUAADreamer 2024-04-25 21:15:16 +08:00
  • 266fe908e3 Merge branch 'main' of https://github.com/BUAADreamer/LLaMA-Factory BUAADreamer 2024-04-25 21:08:40 +08:00
  • dbd905438b add some BUAADreamer 2024-04-25 21:08:32 +08:00
  • d64c87f928 Merge pull request #3449 from hiyouga/mllm hoshi-hiyouga 2024-04-25 20:58:16 +08:00
  • 29eebef696 add webui backend option hiyouga 2024-04-25 20:49:23 +08:00
  • 7bfbcb1fe3 vllm + lora support hiyouga 2024-04-25 20:24:31 +08:00
  • 9b210cf4b3 rm some BUAADreamer 2024-04-25 20:09:43 +08:00
  • f74e640565 Merge branch 'hiyouga:main' into main BUAADreamer 2024-04-25 20:02:50 +08:00
  • d1d08d066a merge data part to the text stream BUAADreamer 2024-04-25 19:58:47 +08:00
  • 6be321b5da fix #3374 hiyouga 2024-04-25 19:56:49 +08:00
  • 3c792174db merge data part to the text stream BUAADreamer 2024-04-25 19:19:59 +08:00
  • 9aeb88c426 add export_device in webui #3333 hiyouga 2024-04-25 19:02:32 +08:00
  • 00e2a272ef merge model part to the text stream BUAADreamer 2024-04-25 08:20:41 +08:00
  • 5142349661 remove error BUAADreamer 2024-04-25 01:01:59 +08:00
  • 0e3cc52327 remove conflicts BUAADreamer 2024-04-25 00:56:06 +08:00
  • 6c1db2d012 remove conflicts BUAADreamer 2024-04-25 00:34:22 +08:00
  • 12c51655ce add llava and instructblip BUAADreamer 2024-04-25 00:22:43 +08:00
  • 36be12a3b7 update tool template hiyouga 2024-04-25 00:21:34 +08:00
  • 21fac4c98c fix log level hiyouga 2024-04-24 23:42:59 +08:00
  • 83404c4fa9 support new special token #3420 hiyouga 2024-04-24 23:39:31 +08:00
  • 12f852b8d4 fix phi template hoshi-hiyouga 2024-04-24 13:55:14 +08:00
  • a88873116a fix webchatmodel hoshi-hiyouga 2024-04-24 13:54:21 +08:00
  • 7cfcd69c64 fix inference in llamaboard hoshi-hiyouga 2024-04-24 13:53:39 +08:00
  • a5eabbe933 add olmo 1.7 hiyouga 2024-04-24 05:50:50 +08:00
  • aa25716a5d add dbrx and jamba models hiyouga 2024-04-24 05:39:52 +08:00
  • 94c8219575 fix bug hiyouga 2024-04-24 05:21:18 +08:00
  • ad24a2a0c9 fix bug hiyouga 2024-04-24 05:10:07 +08:00
  • c05027d14a remove redundant code hiyouga 2024-04-24 05:02:18 +08:00
  • 5420905a2e support unsloth generate hiyouga 2024-04-24 04:46:53 +08:00
  • 03f2e3284a refactor patcher hiyouga 2024-04-24 03:02:23 +08:00
  • d2bb1b3a6b reenable sdpa and fast tok by default hiyouga 2024-04-24 02:18:44 +08:00
  • 35c4a2c212 fix #3347 #3387 hiyouga 2024-04-24 01:30:16 +08:00
  • 1e4010a1fb support phi-3 hiyouga 2024-04-24 00:28:53 +08:00
  • 1451297c78 add multimodal LLM BLIP-2 and InstructBLIP BUAADreamer 2024-04-23 19:22:42 +08:00
  • 0b99b13786 add multimodal LLM BLIP-2 and InstructBLIP BUAADreamer 2024-04-23 18:47:03 +08:00
  • f5edbf2b49 Merge branch 'hiyouga:main' into main BUAADreamer 2024-04-23 18:46:12 +08:00
  • ab6dc0ea30 add multimodal LLM BLIP-2 and InstructBLIP BUAADreamer 2024-04-23 18:45:43 +08:00
  • 79d34ce0f3 update examples hiyouga 2024-04-23 18:29:46 +08:00
  • 1d2e372a8e update readme hiyouga 2024-04-22 17:09:17 +08:00
  • f6a53d83c8 update readme hiyouga 2024-04-22 00:51:35 +08:00
  • 4ec56dd958 update readme hiyouga 2024-04-22 00:42:25 +08:00
  • ba06eb65ca update readme and examples hiyouga 2024-04-22 00:37:32 +08:00
  • be716972fe remove extras hiyouga 2024-04-22 00:35:41 +08:00
  • 719585a128 update readme hiyouga 2024-04-22 00:21:01 +08:00
  • 348f29aa50 set dev version hiyouga 2024-04-21 23:14:30 +08:00
  • c8fe3f544b release v0.6.3 v0.6.3 hiyouga 2024-04-21 23:13:23 +08:00
  • 0f1ad7140f fix #3366 hiyouga 2024-04-21 21:34:25 +08:00
  • 233e167f68 fix optimizers hiyouga 2024-04-21 20:40:54 +08:00
  • 1d341dcd83 fix #3365 hiyouga 2024-04-21 19:20:18 +08:00
  • d16561e7a4 fix bug in galore optimizer hiyouga 2024-04-21 18:53:22 +08:00
  • f8e219dc81 fix mod stuff hiyouga 2024-04-21 18:11:10 +08:00
  • 3365cc8cf0 Merge pull request #3338 from astramind-ai/main hoshi-hiyouga 2024-04-21 18:05:52 +08:00
  • 3a5e68b7d9 fix #3348 hoshi-hiyouga 2024-04-20 10:34:09 +08:00
  • 0cb596fee1 add dpo mix dataset hiyouga 2024-04-20 01:31:38 +08:00
  • b3b5b530d1 fix #3352 hiyouga 2024-04-19 22:40:01 +08:00
  • 9225c15c88 fix llama3 template hiyouga 2024-04-19 15:46:51 +08:00
  • abd9fed445 fix small typo Marco 2024-04-18 20:33:29 +02:00
  • 44cda2eece Added Mixture of Depths Marco 2024-04-18 20:31:24 +02:00
  • 8397808d1d support llama3 hoshi-hiyouga 2024-04-19 01:13:50 +08:00
  • 9e1bd6420d fix #3324 hiyouga 2024-04-18 15:34:45 +08:00
  • 619264c854 tiny fix hiyouga 2024-04-18 00:22:17 +08:00
  • 1ebac62e3d update readme hiyouga 2024-04-17 23:40:49 +08:00
  • ce9bdb3509 add mixtral 8x22B models hiyouga 2024-04-17 23:35:59 +08:00
  • 0c8d6369ac add CodeQwen models hiyouga 2024-04-17 23:27:22 +08:00
  • bee796f6b5 fix #3316 hiyouga 2024-04-17 22:54:34 +08:00
  • 9f6349a333 fix #3317 hiyouga 2024-04-17 22:17:19 +08:00
  • 171a029c5e lint hiyouga 2024-04-16 18:21:09 +08:00
  • eaefaa0fe0 Merge pull request #3291 from codemayq/main hoshi-hiyouga 2024-04-16 18:12:09 +08:00
  • d301f0a64b Update parser.py hiyouga 2024-04-16 18:09:31 +08:00
  • 0a1578e4e3 update readme and gradio version hiyouga 2024-04-16 18:09:16 +08:00
  • a4167fd925 support badam for all stages hiyouga 2024-04-16 17:44:48 +08:00
  • 42084e08ae Merge pull request #3287 from Ledzy/badam hoshi-hiyouga 2024-04-16 17:32:16 +08:00
  • 9d23f5dc89 Update utils.py hoshi-hiyouga 2024-04-16 17:30:12 +08:00
  • 5978427ae0 Update trainer.py hoshi-hiyouga 2024-04-16 17:29:52 +08:00
  • c7c216069c Update utils.py hoshi-hiyouga 2024-04-16 17:29:30 +08:00
  • cde9d1b917 Update patcher.py hoshi-hiyouga 2024-04-16 17:29:19 +08:00
  • 96213f04b0 Update adapter.py hoshi-hiyouga 2024-04-16 17:28:12 +08:00
  • 7ecea08b9b Update parser.py hoshi-hiyouga 2024-04-16 17:27:25 +08:00
  • 191971865d Update parser.py hoshi-hiyouga 2024-04-16 17:27:02 +08:00
  • ff4f587dd9 Update finetuning_args.py hoshi-hiyouga 2024-04-16 17:26:30 +08:00
  • de728d0371 Update sft.sh hoshi-hiyouga 2024-04-16 17:25:40 +08:00
  • d08e09642d Update requirements.txt hoshi-hiyouga 2024-04-16 17:10:17 +08:00
  • 351493b183 Update setup.py hoshi-hiyouga 2024-04-16 17:10:02 +08:00
  • 86ab47e121 remove badam from core requirements Jonery 2024-04-16 12:25:50 +08:00
  • 6dd6b3e396 resolve gradient checkpointing issue. Jonery 2024-04-16 12:05:27 +08:00
  • 5f1418a68b add check codingma 2024-04-16 10:56:39 +08:00
  • 7b97a79efc support for previewing custom dataset in directory format codingma 2024-04-16 10:43:14 +08:00
  • ce4f653121 add empty template hiyouga 2024-04-16 03:10:02 +08:00
  • b053c6454e update readme hiyouga 2024-04-16 02:36:54 +08:00
  • ebf0f4a77c update readme hiyouga 2024-04-16 02:35:36 +08:00
  • efa808069a support unsloth 2024.4 hiyouga 2024-04-16 00:25:03 +08:00
  • b5c5283dd6 add codegemma hiyouga 2024-04-16 00:11:15 +08:00
  • b638c65519 support cohere commandR #3184 hiyouga 2024-04-15 23:26:42 +08:00
  • d4d471450f Feature BAdam Jonery 2024-04-15 23:15:27 +08:00
  • 3144bdec2c Merge pull request #3254 from marko1616/feature/Add-support-for-CohereForAI/c4ai-command-r-plus hoshi-hiyouga 2024-04-15 22:59:35 +08:00
  • c6d6c4c209 Update template.py hoshi-hiyouga 2024-04-15 22:58:01 +08:00
  • f5f1589662 Update constants.py hoshi-hiyouga 2024-04-15 22:56:55 +08:00