kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,331 Commits 1 Branch 0 Tags
3a666832c119606a8d5baf4694b96569bee18659
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
hiyouga 3a666832c1 add cal_ppl script 2024-05-04 22:02:25 +08:00
hiyouga 57a39783d1 update readme 2024-05-04 17:01:21 +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 d4283bb6bf update readme 2024-05-04 00:43:53 +08:00
hiyouga 9d2ce57345 update readme and webui launch 2024-05-04 00:43:02 +08:00
hiyouga 1409654cef update readme 2024-05-04 00:31:02 +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 39e964a97a Update prepare.sh 2024-05-02 17:16:02 +08:00
hiyouga 9433c8c215 fix badam configs 2024-05-02 02:47:04 +08:00
hoshi-hiyougaandGitHub f1c0eedeb3 Merge pull request #3487 from codemayq/main 
support BAdam in WebUI
 2024-05-02 02:38:01 +08:00
hoshi-hiyougaandGitHub dcd53cb89a Update train.py 2024-05-02 02:21:27 +08:00
hoshi-hiyougaandGitHub 282b5d5b1f Merge pull request #3490 from khazic/main 
Added the second sharegpt format
 2024-05-02 02:15:23 +08:00
hoshi-hiyougaandGitHub d4d9180c40 Update README_zh.md 2024-05-02 02:14:55 +08:00
hoshi-hiyougaandGitHub b072ec9d1b Update README.md 2024-05-02 02:13:46 +08:00
hiyouga 32347901d4 fix setup 2024-04-28 03:49:13 +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 5ee04d418c update readme 2024-04-26 23:39:19 +08:00
hoshi-hiyougaandGitHub 8f91420223 Merge pull request #3471 from BUAADreamer/main 
add llava_150k en/zh mllm sft data
 2024-04-26 23:36:41 +08:00
hoshi-hiyougaandGitHub 456ad61ac5 Update dataset_info.json 2024-04-26 23:36:13 +08:00
hoshi-hiyougaandGitHub c29b257007 Update dataset_info.json 2024-04-26 23:34:34 +08:00
hiyouga 168f56683a release v0.7.0 2024-04-26 23:18:00 +08:00
hiyouga 031775ade8 update readme 2024-04-26 20:09:14 +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 e83e2fa897 update readme 2024-04-26 05:49:26 +08:00
hoshi-hiyougaandGitHub 20bc959e2f Merge pull request #3454 from hiyouga/mllm 
Support fine-tuning LLaVA-1.5 MLLM @BUAADreamer
 2024-04-26 05:46:29 +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 c20f750d11 Merge pull request #3450 from BUAADreamer/mllm 
Add Multimodal LLM Finetuning
 2024-04-26 05:30:30 +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 f8c26e6a34 Update dataset_info.json 2024-04-26 03:03:36 +08:00
hoshi-hiyougaandGitHub 5ef293387f Update mllm_demo.json 2024-04-26 02:58:45 +08:00
hoshi-hiyougaandGitHub 7dcae3dba3 Update and rename llava_instruct_example.json to mllm_demo.json 2024-04-26 02:57:54 +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
hoshi-hiyougaandGitHub fcfbd8c300 Merge pull request #3449 from hiyouga/mllm 
add webui backend option
 2024-04-25 20:58:16 +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
hiyouga 8d66435664 fix #3374 2024-04-25 19:56:49 +08:00
hiyouga 3a7c1286ce add export_device in webui #3333 2024-04-25 19:02:32 +08:00
hiyouga aa16ff6205 update tool template 2024-04-25 00:21:34 +08:00
hiyouga 7fbe8add8f fix log level 2024-04-24 23:42:59 +08:00
hiyouga 297fb8ead3 support new special token #3420 2024-04-24 23:39:31 +08:00
hoshi-hiyougaandGitHub e5d23c053a fix phi template 2024-04-24 13:55:14 +08:00
hoshi-hiyougaandGitHub 4c71c314fb fix webchatmodel 2024-04-24 13:54:21 +08:00
hoshi-hiyougaandGitHub f36057ea03 fix inference in llamaboard 2024-04-24 13:53:39 +08:00
hiyouga 44a43ee152 add olmo 1.7 2024-04-24 05:50:50 +08:00
hiyouga 69eb03a8fe add dbrx and jamba models 2024-04-24 05:39:52 +08:00
hiyouga 73ff9c834b fix bug 2024-04-24 05:21:18 +08:00
hiyouga 8f44dce08a fix bug 2024-04-24 05:10:07 +08:00
hiyouga 667ce08b27 remove redundant code 2024-04-24 05:02:18 +08:00
hiyouga b1deb0a0b9 support unsloth generate 2024-04-24 04:46:53 +08:00
hiyouga aa2b79eb23 refactor patcher 2024-04-24 03:02:23 +08:00
hiyouga 07737a3d2d reenable sdpa and fast tok by default 2024-04-24 02:18:44 +08:00
hiyouga 707f0b1d5d fix #3347 #3387 2024-04-24 01:30:16 +08:00
hiyouga 1a13f05555 support phi-3 2024-04-24 00:28:53 +08:00
hiyouga 2efd9b6ba0 update examples 2024-04-23 18:29:46 +08:00
hiyouga 5722ada12b Update wechat.jpg 2024-04-23 17:12:33 +08:00
hiyouga db7f3b9784 update readme 2024-04-22 17:09:17 +08:00
hiyouga 836ca05586 update readme 2024-04-22 00:51:35 +08:00
hiyouga 34d66a3a85 update readme 2024-04-22 00:42:25 +08:00
hiyouga a1f1fac33b update readme and examples 2024-04-22 00:37:32 +08:00
hiyouga ddbd29d777 remove extras 2024-04-22 00:35:41 +08:00
hiyouga 1197513a16 Update wechat.jpg 2024-04-22 00:22:58 +08:00
hiyouga a83e7587a0 update readme 2024-04-22 00:21:01 +08:00
hiyouga 3e1bf8325c set dev version 2024-04-21 23:14:30 +08:00
hiyouga e0d6b72d56 release v0.6.3 2024-04-21 23:13:23 +08:00
hiyouga 4469a3237d fix #3366 2024-04-21 21:34:25 +08:00
hiyouga fbbe0dba2f fix optimizers 2024-04-21 20:40:54 +08:00
hiyouga a1d31ffc8c fix #3365 2024-04-21 19:20:18 +08:00
hiyouga 5c62881c5a fix bug in galore optimizer 2024-04-21 18:53:22 +08:00
hiyouga f58425ab45 fix mod stuff 2024-04-21 18:11:10 +08:00
hoshi-hiyougaandGitHub d0273787be Merge pull request #3338 from astramind-ai/main 
Adding Mixture of Depth
 2024-04-21 18:05:52 +08:00
hoshi-hiyouga 1fa287fd63 fix #3348 2024-04-20 10:34:09 +08:00
hiyouga 6339edefff add dpo mix dataset 2024-04-20 01:31:38 +08:00
hiyouga ba559a659a fix #3352 2024-04-19 22:40:01 +08:00
hiyouga 14a605a2da fix llama3 template 2024-04-19 15:46:51 +08:00
hoshi-hiyouga 2aaaede247 support llama3 2024-04-19 01:13:50 +08:00
hiyouga 942362d008 fix #3324 2024-04-18 15:34:45 +08:00
hiyouga 3b43a3b7c5 tiny fix 2024-04-18 00:22:17 +08:00
hiyouga e2f1c6fc6a update readme 2024-04-17 23:40:49 +08:00
hiyouga cab0598fd0 add mixtral 8x22B models 2024-04-17 23:35:59 +08:00
hiyouga 5f86053d75 add CodeQwen models 2024-04-17 23:27:22 +08:00
hiyouga c9a477322d fix #3316 2024-04-17 22:54:34 +08:00