kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • f32eefae3d Update generating_args.py hoshi-hiyouga 2024-05-07 00:28:16 +08:00
  • 7ae7ae64f0 Update generating_args.py hoshi-hiyouga 2024-05-07 00:27:56 +08:00
  • d6ca7853fa Merge pull request #3588 from ZeyuTeng96/patch-1 hoshi-hiyouga 2024-05-07 00:06:11 +08:00
  • c3910ab98a Update dataset_info.json hoshi-hiyouga 2024-05-07 00:05:45 +08:00
  • f50c365871 update readme hiyouga 2024-05-06 23:34:59 +08:00
  • a153039380 fix gradio args hiyouga 2024-05-06 23:33:06 +08:00
  • c8cd00bec6 Merge pull request #3596 from hiyouga/dev_doc hoshi-hiyouga 2024-05-06 23:10:38 +08:00
  • 047313f48e update examples hiyouga 2024-05-06 23:07:55 +08:00
  • f02f87c6fb update example docs hiyouga 2024-05-06 22:51:02 +08:00
  • 34d33e2257 update docs hiyouga 2024-05-06 21:47:00 +08:00
  • 044af36442 update hf_hub_url for nectar_rm in dataset_info ZeyuTeng96 2024-05-06 16:44:50 +08:00
  • 28ae947161 The training efficiency of the Ascend 910A has been significantly enhanced, leveraging the full computational power of the NPU (Neural Processing Unit) and the capabilities of torch_npu, a PyTorch library optimized for NPUs. This improvement has resulted in a remarkable tenfold increase in efficiency. zhouwei 2024-05-06 13:29:59 +08:00
  • 80645751bc ”add stop parameter in chat.py“ zhaonx96 2024-05-06 10:10:00 +08:00
  • 1abd55dd59 Merge branch 'main' of https://github.com/zhaonx/LLaMA-Factory into dev zhaonx96 2024-05-06 10:09:00 +08:00
  • a34f526f10 Merge pull request #3578 from pha123661/main hoshi-hiyouga 2024-05-05 23:41:58 +08:00
  • eeb415f6fa Fix badam example outdated argument Oscar 2024-05-05 23:35:19 +08:00
  • 845d5acd03 update wechat codingma 2024-05-05 15:31:47 +08:00
  • bd095eeb73 add version and help to cli hiyouga 2024-05-05 02:44:35 +08:00
  • 177604fb6b fix eval scripts hiyouga 2024-05-05 00:53:07 +08:00
  • af596988b1 update webui hiyouga 2024-05-05 00:17:54 +08:00
  • c1a53a0deb update scripts hiyouga 2024-05-04 23:05:17 +08:00
  • 25aeaae51b add avg ppl hiyouga 2024-05-04 22:35:31 +08:00
  • 76a077bdce update ppl script hiyouga 2024-05-04 22:13:14 +08:00
  • 3a666832c1 add cal_ppl script hiyouga 2024-05-04 22:02:25 +08:00
  • 57a39783d1 update readme hiyouga 2024-05-04 17:01:21 +08:00
  • e984ba3167 remove empty stream response hiyouga 2024-05-04 16:13:52 +08:00
  • 941924fdbd fix async stream api response hiyouga 2024-05-04 16:11:18 +08:00
  • ed8f8be752 update api and support abort eval in webui hiyouga 2024-05-04 15:59:15 +08:00
  • d4283bb6bf update readme hiyouga 2024-05-04 00:43:53 +08:00
  • 9d2ce57345 update readme and webui launch hiyouga 2024-05-04 00:43:02 +08:00
  • 1409654cef update readme hiyouga 2024-05-04 00:31:02 +08:00
  • 24cc93ab15 fix eval in webui hiyouga 2024-05-04 00:19:19 +08:00
  • 510e64ee70 fix webui resume hiyouga 2024-05-03 23:15:19 +08:00
  • 3010154adb fix slow op in dpo/orpo trainer hiyouga 2024-05-03 23:06:52 +08:00
  • 9585838ebe fix callback log multigpu #3559 hiyouga 2024-05-03 21:24:27 +08:00
  • 5e6f808e3c enable tqdm in webui hiyouga 2024-05-03 04:42:50 +08:00
  • 17d2e5147e fix gen_args hiyouga 2024-05-03 04:24:50 +08:00
  • 530f6b49bb fix colab gradio hiyouga 2024-05-03 03:54:46 +08:00
  • 245fe47ece update webui and add CLIs hiyouga 2024-05-03 02:58:23 +08:00
  • 39e964a97a Update prepare.sh hiyouga 2024-05-02 17:16:02 +08:00
  • 9433c8c215 fix badam configs hiyouga 2024-05-02 02:47:04 +08:00
  • f1c0eedeb3 Merge pull request #3487 from codemayq/main hoshi-hiyouga 2024-05-02 02:38:01 +08:00
  • dcd53cb89a Update train.py hoshi-hiyouga 2024-05-02 02:21:27 +08:00
  • 282b5d5b1f Merge pull request #3490 from khazic/main hoshi-hiyouga 2024-05-02 02:15:23 +08:00
  • d4d9180c40 Update README_zh.md hoshi-hiyouga 2024-05-02 02:14:55 +08:00
  • b072ec9d1b Update README.md hoshi-hiyouga 2024-05-02 02:13:46 +08:00
  • 42edc81585 "add support for vllm api stop parameter" zhaonx 2024-04-30 17:17:09 +08:00
  • b4a212f934 Merge branch 'hiyouga:main' into main codingma 2024-04-30 10:02:41 +08:00
  • d27e6a46b4 update wechat codingma 2024-04-30 09:40:04 +08:00
  • ce17eccf45 Update README_zh.md Lao 2024-04-28 23:31:37 +08:00
  • 288911fc7b Upgrade the second sharegpt format khazic 2024-04-28 14:30:05 +08:00
  • d1ba32e4bb added the second sharegpt format khazic 2024-04-28 14:27:45 +08:00
  • 26f7170393 support BAdam in WebUI codingma 2024-04-28 11:31:34 +08:00
  • e898fabbe3 Merge pull request #3484 from codemayq/main codingma 2024-04-28 08:40:08 +08:00
  • 850f9b554f update wechat codingma 2024-04-28 08:37:19 +08:00
  • 32347901d4 fix setup hiyouga 2024-04-28 03:49:13 +08:00
  • b3e33c703e fix llava rlhf hiyouga 2024-04-28 03:01:49 +08:00
  • 4dbbce21d5 add models to 0.7.0 hiyouga 2024-04-28 01:50:30 +08:00
  • 5ee04d418c update readme hiyouga 2024-04-26 23:39:19 +08:00
  • 8f91420223 Merge pull request #3471 from BUAADreamer/main hoshi-hiyouga 2024-04-26 23:36:41 +08:00
  • 456ad61ac5 Update dataset_info.json hoshi-hiyouga 2024-04-26 23:36:13 +08:00
  • c29b257007 Update dataset_info.json hoshi-hiyouga 2024-04-26 23:34:34 +08:00
  • a177872010 add llava_150k en/zh mllm sft data BUAADreamer 2024-04-26 23:18:58 +08:00
  • 168f56683a release v0.7.0 hiyouga 2024-04-26 23:18:00 +08:00
  • 031775ade8 update readme hiyouga 2024-04-26 20:09:14 +08:00
  • 375b25131b support Qwen1.5 110B hiyouga 2024-04-26 19:59:22 +08:00
  • fc67b736ba fix llava qlora hiyouga 2024-04-26 18:00:23 +08:00
  • cd3a960f81 add llava to llamaboard hiyouga 2024-04-26 06:41:35 +08:00
  • e83e2fa897 update readme hiyouga 2024-04-26 05:49:26 +08:00
  • 20bc959e2f Merge pull request #3454 from hiyouga/mllm hoshi-hiyouga 2024-04-26 05:46:29 +08:00
  • 27ba1b63ce update readme hiyouga 2024-04-26 05:44:30 +08:00
  • e057c8de48 support mllm hf inference hiyouga 2024-04-26 05:34:58 +08:00
  • c20f750d11 Merge pull request #3450 from BUAADreamer/mllm hoshi-hiyouga 2024-04-26 05:30:30 +08:00
  • 7f3bd35c0e Update preprocess.py hoshi-hiyouga 2024-04-26 04:10:28 +08:00
  • fcd09112d5 Update aligner.py hoshi-hiyouga 2024-04-26 03:48:34 +08:00
  • f62cadb258 Update parser.py hoshi-hiyouga 2024-04-26 03:35:39 +08:00
  • 3408af236f Update loader.py hoshi-hiyouga 2024-04-26 03:33:07 +08:00
  • e16f128dc3 Update workflow.py hoshi-hiyouga 2024-04-26 03:29:12 +08:00
  • 7d812ed841 Update loader.py hoshi-hiyouga 2024-04-26 03:22:40 +08:00
  • f8c26e6a34 Update dataset_info.json hoshi-hiyouga 2024-04-26 03:03:36 +08:00
  • 5ef293387f Update mllm_demo.json hoshi-hiyouga 2024-04-26 02:58:45 +08:00
  • 7dcae3dba3 Update and rename llava_instruct_example.json to mllm_demo.json hoshi-hiyouga 2024-04-26 02:57:54 +08:00
  • 860549b99b update hparam name hoshi-hiyouga 2024-04-26 02:49:39 +08:00
  • 646a7885e7 delete llava template (use vicuna) hoshi-hiyouga 2024-04-26 02:20:47 +08:00
  • a7ead1440f modify some bug BUAADreamer 2024-04-25 22:59:46 +08:00
  • ece78a6d6a modify some style BUAADreamer 2024-04-25 22:40:53 +08:00
  • d29f3798f6 modify some style BUAADreamer 2024-04-25 22:40:25 +08:00
  • 31420f7b31 merge some func BUAADreamer 2024-04-25 22:35:17 +08:00
  • c27f7fbf62 modify some style BUAADreamer 2024-04-25 22:04:09 +08:00
  • 2d4ded535f modify some style BUAADreamer 2024-04-25 21:58:18 +08:00
  • 2cab2d42fb make dataset script BUAADreamer 2024-04-25 21:32:01 +08:00
  • 235b411370 modify style BUAADreamer 2024-04-25 21:29:50 +08:00
  • fc0fa9f048 modify style BUAADreamer 2024-04-25 21:27:48 +08:00
  • 1dcabafe72 modify style BUAADreamer 2024-04-25 21:15:16 +08:00
  • 43d7ad5ecc Merge branch 'main' of https://github.com/BUAADreamer/LLaMA-Factory BUAADreamer 2024-04-25 21:08:40 +08:00
  • 94ad744941 add some BUAADreamer 2024-04-25 21:08:32 +08:00
  • fcfbd8c300 Merge pull request #3449 from hiyouga/mllm hoshi-hiyouga 2024-04-25 20:58:16 +08:00
  • b45939e139 add webui backend option hiyouga 2024-04-25 20:49:23 +08:00
  • 28571da80a vllm + lora support hiyouga 2024-04-25 20:24:31 +08:00
  • eefcd105c1 rm some BUAADreamer 2024-04-25 20:09:43 +08:00