kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
896 Commits 1 Branch 0 Tags
869fd208a81efd8a2e4785549684978fc2e17d64
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
hoshi-hiyougaandGitHub 869fd208a8 Update README.md 2024-02-20 16:07:55 +08:00
hoshi-hiyougaandGitHub 175a48d79d Update README_zh.md 2024-02-20 16:06:59 +08:00
hiyouga ba998c67ab update webui 2024-02-19 16:49:58 +08:00
hiyouga 26912cd816 add test scripts 2024-02-19 02:09:13 +08:00
hiyouga d46977edf5 Update wechat.jpg 2024-02-18 18:15:22 +08:00
hiyouga e4e86a73f1 fix safetensors 2024-02-18 18:12:16 +08:00
hiyouga 22acab8aff fix #2481 2024-02-15 19:07:47 +08:00
hiyouga 7924ffc55d support llama pro #2338 , add rslora 2024-02-15 02:27:36 +08:00
hoshi-hiyougaandGitHub 8a1b389086 Merge pull request #2474 from younesbelkada/add-hf-tags 
FEAT: add HF tags for models that have been trained with llama-factory
 2024-02-14 10:26:03 +08:00
hiyouga 12b2066e34 fix #2471 2024-02-12 21:07:46 +08:00
hiyouga 91d09a01ac add option to disable version check 2024-02-10 22:31:23 +08:00
hiyouga a754f6e9ec update data/readme 2024-02-10 21:04:29 +08:00
hiyouga a5fb2806cd update default template 2024-02-10 16:44:47 +08:00
hiyouga 7d2dc83c5e improve aligner 2024-02-10 16:39:19 +08:00
hoshi-hiyougaandGitHub 388b705a8d Merge pull request #2462 from mnmueller/main 
Enable Parsing of SlimOrca
 2024-02-09 22:55:48 +08:00
hiyouga 54ea9684ed improve fix tokenizer 2024-02-09 14:53:14 +08:00
hoshi-hiyougaandGitHub d0daaa01f9 Merge pull request #2423 from mayflower/main 
Support for german sft and dpo
 2024-02-07 15:58:20 +08:00
hiyouga d6775c6522 Update tests.yml 2024-02-07 01:18:22 +08:00
hiyouga 88a1bc9773 lint 2024-02-07 01:10:04 +08:00
hiyouga aacc823b0f Update pyproject.toml 2024-02-07 00:45:58 +08:00
hiyouga 0ae9a16b9d update gc kwargs 2024-02-07 00:38:24 +08:00
hiyouga ebf31b62eb fix #2438 2024-02-06 15:23:08 +08:00
hiyouga 85622ae757 add models 2024-02-06 14:57:23 +08:00
hiyouga ccabb5b04a support qwen1.5 2024-02-06 00:10:51 +08:00
hoshi-hiyougaandGitHub 7f48c599eb fix #2436 
Update test_toolcall.py
 2024-02-05 22:55:28 +08:00
hoshi-hiyougaandGitHub b5007afb19 Update test_toolcall.py 2024-02-05 22:51:03 +08:00
hoshi-hiyougaandGitHub d4994235f0 Update test_toolcall.py 2024-02-05 22:50:43 +08:00
hiyouga 3dc86c4af9 fix #2421 2024-02-04 21:02:55 +08:00
hiyouga db0ab4d601 fix reserved label len 2024-02-04 17:54:26 +08:00
hiyouga 19d33ede13 fix #2420 2024-02-04 15:51:47 +08:00
hiyouga b988ce0a0c fix #2189 2024-02-04 00:47:37 +08:00
hiyouga 38e63bfd28 bump up transformers version 2024-02-04 00:01:16 +08:00
hiyouga 51df865734 fix #2397 2024-02-03 23:45:31 +08:00
hiyouga 6545c02790 add hint for freeze #2412 2024-02-03 23:38:56 +08:00
hiyouga 4ecadc3512 fix #2376 2024-02-03 23:14:31 +08:00
hiyouga 901faa16cc support minicpm #2404 2024-02-03 22:36:46 +08:00
hoshi-hiyougaandGitHub 2eaaa9522f Merge pull request #2411 from lxsyz/main 
fix eos_token_id=0 bug
 2024-02-02 17:38:16 +08:00
hiyouga ec70eb5d8d Update wechat.jpg 2024-02-01 11:01:12 +08:00
hiyouga 39bd5bd524 fix #2388 2024-01-31 17:23:56 +08:00
hiyouga 521ad76552 fix autoset attn impl, update data readme 2024-01-31 11:58:07 +08:00
hiyouga 60733275f8 Update wechat.jpg 2024-01-25 13:02:49 +08:00
hiyouga 2bc30763e9 fix #2320 2024-01-24 16:19:18 +08:00
hoshi-hiyougaandGitHub 51ad35b3c7 Merge pull request #2319 from ftgreat/main 
Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3
 2024-01-24 15:32:26 +08:00
hiyouga dbaaa4546e Update dataset_info.json 2024-01-23 00:10:32 +08:00
hiyouga e4ba1deedf add hint 2024-01-22 23:32:01 +08:00
hoshi-hiyougaandGitHub 8e4b3a959a Merge pull request #2283 from A-Cepheus/main 
fix: ZeRO3 does not work with MoE models
 2024-01-22 23:28:45 +08:00
hoshi-hiyougaandGitHub bdc9eff635 Update patcher.py 2024-01-22 23:27:39 +08:00
hoshi-hiyougaandGitHub bb5a3b85a6 Update tests.yml 2024-01-22 23:22:15 +08:00
hoshi-hiyougaandGitHub 087476da99 Create tests.yml 2024-01-22 23:13:04 +08:00
hiyouga b2fb0eca56 fix #2282 and update tool prompt 2024-01-22 22:27:30 +08:00
hiyouga 6fc2d5cc03 add orion models 2024-01-22 21:26:53 +08:00
hiyouga 486cc8d360 add array param format 2024-01-21 22:17:48 +08:00
hiyouga 37ec5deaec update tool test 2024-01-21 19:41:46 +08:00
hiyouga f51d48ea08 fix api 2024-01-21 19:15:27 +08:00
hiyouga e0a717aa3a fix #2268 2024-01-21 14:11:38 +08:00
hiyouga 3bc301be02 tiny fix 2024-01-21 13:26:12 +08:00
hoshi-hiyougaandGitHub ea6db72631 Merge pull request #2266 from yhyu13/fix_export_model_dtype 
Remove manully set use_cache; torch_dtype is not str, save model as b…
 2024-01-21 12:40:39 +08:00
hoshi-hiyougaandGitHub 2533be5e2a Merge branch 'main' into fix_export_model_dtype 2024-01-21 12:40:24 +08:00
hoshi-hiyougaandGitHub 662b9a9dcf Update tuner.py 2024-01-21 12:39:38 +08:00
hoshi-hiyougaandGitHub 11f612deab Merge pull request #2262 from fenglui/main 
fix torch_dtype check of export_model
 2024-01-21 12:34:37 +08:00
hiyouga 3c1e256992 format 2024-01-21 12:34:17 +08:00
hoshi-hiyougaandGitHub 3ba75dc071 Merge pull request #2264 from seoeaa/main 
add russian lang
 2024-01-21 12:25:24 +08:00
hiyouga a0d59aa4ec release v0.5.0 (real) 2024-01-21 01:54:49 +08:00
hiyouga 3e982cc714 finish agent 2024-01-21 01:47:33 +08:00
hiyouga 55f707196e fix api 2024-01-21 00:03:09 +08:00
hiyouga a9c18255aa fix internlm2 template 2024-01-20 23:33:50 +08:00
hiyouga c550987a72 fix cli_demo 2024-01-20 23:27:10 +08:00
hiyouga cf818a2598 fix #2260 2024-01-20 23:22:09 +08:00
hiyouga 71cfdc2658 release v0.5.0 2024-01-20 20:21:39 +08:00
hiyouga 638234ceee format style 2024-01-20 20:15:56 +08:00
hiyouga f6d6e00337 fix tests 2024-01-20 19:58:04 +08:00
hiyouga 38af076a75 support longlora for main branch 2024-01-20 19:25:22 +08:00
hoshi-hiyougaandGitHub bb92cdd0db Merge pull request #2201 from liu-zichen/token_embed_resize 
support resize embed for zero3
 2024-01-20 17:45:38 +08:00
hiyouga 8cbe4e9609 add upcast_lmhead option 2024-01-19 23:54:25 +08:00
hiyouga 0ff9a1fb4f set use_reentrant=False 2024-01-19 23:29:54 +08:00
hiyouga 12043aab9c fix #2249 2024-01-19 21:44:32 +08:00
hiyouga b6ec112beb add bf16 lora option 2024-01-19 16:29:03 +08:00
hiyouga 35aef8b287 fix function formatter 2024-01-18 16:01:07 +08:00
hiyouga ddd48ce8ab Update tuner.py 2024-01-18 15:06:02 +08:00
hiyouga b5ef993e34 update wechat 2024-01-18 14:54:38 +08:00
hiyouga a73a979afd fix templates 2024-01-18 14:49:52 +08:00
hiyouga 5edf7cce0e fix rm dataset 2024-01-18 14:45:37 +08:00
hiyouga 5ff10fac4f fix pretrain data loader 2024-01-18 14:42:52 +08:00
hoshi-hiyougaandGitHub 9986cc6dd1 Merge pull request #2226 from hiyouga/dev 
support function calling
 2024-01-18 14:31:28 +08:00
hiyouga 5608a0da8e update readme 2024-01-18 14:30:48 +08:00
hiyouga 2abfe5fbc2 add tool hint 2024-01-18 13:19:09 +08:00
hiyouga 487dee066f fix dataset 2024-01-18 12:59:30 +08:00
hiyouga f1067d2b58 enable cutoff len 2024-01-18 12:25:42 +08:00
hiyouga 83dbfce8c3 add tool test 2024-01-18 10:26:26 +08:00
hiyouga d9f1cae351 support function calling 2024-01-18 09:54:23 +08:00
hiyouga 28135d787d Update llamafy_internlm2.py 2024-01-18 01:12:31 +08:00
hiyouga 484becae1b Update llamafy_internlm2.py 2024-01-18 01:00:16 +08:00
hiyouga c84a387c2c Update llamafy_internlm2.py 2024-01-18 00:49:31 +08:00
hiyouga f99140d5e8 fix llamafy scripts 2024-01-18 00:37:37 +08:00
hiyouga 7ff4c874d2 fix llamafy_internlm2 2024-01-18 00:26:14 +08:00
hiyouga f1d7ca77b1 add llamafy_internlm2 2024-01-18 00:17:41 +08:00
hiyouga 42859f0734 support export push_to_hub #2183 2024-01-16 23:59:42 +08:00
hiyouga a83fb6d3ff fix #2195 2024-01-16 23:53:50 +08:00
hiyouga 5a207bb723 tiny fix 2024-01-15 23:34:23 +08:00
hoshi-hiyougaandGitHub 3aa8901994 Merge pull request #2194 from junuMoon/patch-1 
fix: typo on README.md
 2024-01-15 20:21:28 +08:00