kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,055 Commits 1 Branch 0 Tags
3382317e32f88ed377d3e7759bdeaf0f2559d22a
Commit Graph
1400 Commits
Author SHA1 Message Date
zhouwei 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. 2024-05-06 13:29:59 +08:00
zhaonx96 80645751bc ”add stop parameter in chat.py“ 2024-05-06 10:10:00 +08:00
zhaonx96 1abd55dd59 Merge branch 'main' of https://github.com/zhaonx/LLaMA-Factory into dev 2024-05-06 10:09:00 +08:00
hiyouga bd095eeb73 add version and help to cli 2024-05-05 02:44:35 +08:00
hiyouga af596988b1 update webui 2024-05-05 00:17:54 +08:00
hiyouga e984ba3167 remove empty stream response 2024-05-04 16:13:52 +08:00
hiyouga 941924fdbd fix async stream api response 2024-05-04 16:11:18 +08:00
hiyouga ed8f8be752 update api and support abort eval in webui 2024-05-04 15:59:15 +08:00
hiyouga 9d2ce57345 update readme and webui launch 2024-05-04 00:43:02 +08:00
hiyouga 24cc93ab15 fix eval in webui 2024-05-04 00:19:19 +08:00
hiyouga 510e64ee70 fix webui resume 2024-05-03 23:15:19 +08:00
hiyouga 3010154adb fix slow op in dpo/orpo trainer 2024-05-03 23:06:52 +08:00
hiyouga 9585838ebe fix callback log multigpu #3559 2024-05-03 21:24:27 +08:00
hiyouga 5e6f808e3c enable tqdm in webui 2024-05-03 04:42:50 +08:00
hiyouga 17d2e5147e fix gen_args 2024-05-03 04:24:50 +08:00
hiyouga 530f6b49bb fix colab gradio 2024-05-03 03:54:46 +08:00
hiyouga 245fe47ece update webui and add CLIs 2024-05-03 02:58:23 +08:00
hiyouga 9433c8c215 fix badam configs 2024-05-02 02:47:04 +08:00
hoshi-hiyougaandGitHub dcd53cb89a Update train.py 2024-05-02 02:21:27 +08:00
zhaonx 42edc81585 "add support for vllm api stop parameter" 2024-04-30 17:17:09 +08:00
codingma 26f7170393 support BAdam in WebUI 2024-04-28 11:31:34 +08:00
hiyouga b3e33c703e fix llava rlhf 2024-04-28 03:01:49 +08:00
hiyouga 4dbbce21d5 add models to 0.7.0 2024-04-28 01:50:30 +08:00
hiyouga 168f56683a release v0.7.0 2024-04-26 23:18:00 +08:00
hiyouga 375b25131b support Qwen1.5 110B 2024-04-26 19:59:22 +08:00
hiyouga fc67b736ba fix llava qlora 2024-04-26 18:00:23 +08:00
hiyouga cd3a960f81 add llava to llamaboard 2024-04-26 06:41:35 +08:00
hiyouga 27ba1b63ce update readme 2024-04-26 05:44:30 +08:00
hiyouga e057c8de48 support mllm hf inference 2024-04-26 05:34:58 +08:00
hoshi-hiyougaandGitHub 7f3bd35c0e Update preprocess.py 2024-04-26 04:10:28 +08:00
hoshi-hiyougaandGitHub fcd09112d5 Update aligner.py 2024-04-26 03:48:34 +08:00
hoshi-hiyougaandGitHub f62cadb258 Update parser.py 2024-04-26 03:35:39 +08:00
hoshi-hiyougaandGitHub 3408af236f Update loader.py 2024-04-26 03:33:07 +08:00
hoshi-hiyougaandGitHub e16f128dc3 Update workflow.py 2024-04-26 03:29:12 +08:00
hoshi-hiyougaandGitHub 7d812ed841 Update loader.py 2024-04-26 03:22:40 +08:00
hoshi-hiyougaandGitHub 860549b99b update hparam name 2024-04-26 02:49:39 +08:00
hoshi-hiyougaandGitHub 646a7885e7 delete llava template (use vicuna) 2024-04-26 02:20:47 +08:00
BUAADreamer a7ead1440f modify some bug 2024-04-25 22:59:46 +08:00
BUAADreamer ece78a6d6a modify some style 2024-04-25 22:40:53 +08:00
BUAADreamer d29f3798f6 modify some style 2024-04-25 22:40:25 +08:00
BUAADreamer 31420f7b31 merge some func 2024-04-25 22:35:17 +08:00
BUAADreamer c27f7fbf62 modify some style 2024-04-25 22:04:09 +08:00
BUAADreamer 2d4ded535f modify some style 2024-04-25 21:58:18 +08:00
BUAADreamer 235b411370 modify style 2024-04-25 21:29:50 +08:00
BUAADreamer fc0fa9f048 modify style 2024-04-25 21:27:48 +08:00
BUAADreamer 1dcabafe72 modify style 2024-04-25 21:15:16 +08:00
BUAADreamer 43d7ad5ecc Merge branch 'main' of https://github.com/BUAADreamer/LLaMA-Factory 2024-04-25 21:08:40 +08:00
BUAADreamer 94ad744941 add some 2024-04-25 21:08:32 +08:00
hiyouga b45939e139 add webui backend option 2024-04-25 20:49:23 +08:00
hiyouga 28571da80a vllm + lora support 2024-04-25 20:24:31 +08:00