kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,156 Commits 1 Branch 0 Tags
50ced257e0a1737dbd73d569f8f706ff452f70aa
Commit Graph
820 Commits
Author SHA1 Message Date
Jonery 7ecb61822b resolve gradient checkpointing issue. 2024-04-16 12:05:27 +08:00
Jonery 06c8908d3f Feature BAdam 2024-04-15 23:15:27 +08:00
hiyouga cce52351b5 update examples 2024-04-15 22:14:34 +08:00
hoshi-hiyougaandGitHub 0e0942d388 Merge pull request #3276 from liu-zichen/fix_mixtral 
fix: turn on output_router_logits of mixtral
 2024-04-15 15:38:16 +08:00
hiyouga efc345c4b0 fix #3273 2024-04-15 15:32:58 +08:00
liuzc 9f4fe62386 fix: mixtral output_router_logits 2024-04-15 12:11:49 +08:00
hiyouga c53a11b6fd fix model card 2024-04-12 17:11:59 +08:00
hiyouga 232642a621 fix #3238 2024-04-12 14:28:11 +08:00
hiyouga 3dfe4cf611 set dev version 2024-04-11 20:27:34 +08:00
hiyouga 9d4c949461 release v0.6.2 2024-04-11 20:08:51 +08:00
hiyouga 51d0a1a19e Merge branch 'main' of https://github.com/hiyouga/LLaMA-Factory 2024-04-10 23:58:18 +08:00
hiyouga a99f5ed0b6 fix #3225 2024-04-10 23:57:59 +08:00
hoshi-hiyougaandGitHub 98bc97d8d2 Update adapter.py 2024-04-10 00:57:51 +08:00
hoshi-hiyougaandGitHub 2111b586b6 Update adapter.py 2024-04-10 00:57:30 +08:00
Erich SchubertandGitHub b5eefe5c4c Pass additional_target to unsloth 
Fixes #3200
 2024-04-09 17:53:40 +02:00
hiyouga 7f6c2486b8 fix quant infer and qwen2moe 2024-04-09 17:12:59 +08:00
hiyouga 9a99fbc86d tiny fix 2024-04-08 21:28:39 +08:00
hoshi-hiyougaandGitHub 4c6c4a0d88 Merge pull request #3161 from hiyouga/feature/add-mediatek-model 
support Breeze-7B
 2024-04-08 20:56:51 +08:00
codingma 7b76b4ca08 add empty line 2024-04-07 18:28:08 +08:00
codingma 34bdcba017 rename template to breeze 2024-04-07 18:27:20 +08:00
codingma 5a780e9eec rename template to breeze 2024-04-07 11:39:54 +08:00
codingma 2565a32bd9 support https://github.com/hiyouga/LLaMA-Factory/issues/3152 2024-04-07 11:34:01 +08:00
sliderSun 1d117b7bb6 fix spell error 2024-04-07 10:59:15 +08:00
sliderSun 21650d467c support Qwen1.5-32B 2024-04-07 10:56:03 +08:00
sliderSun 77044d9ef4 support Qwen1.5-32B 2024-04-07 10:26:13 +08:00
hiyouga a6d943804b tiny fix 2024-04-04 02:19:03 +08:00
hiyouga 4b920f24d3 back to gradio 4.21 and fix chat 2024-04-04 02:07:20 +08:00
hiyouga 5ddcecda50 fix bug in latest gradio 2024-04-04 00:55:31 +08:00
hiyouga 7f6e412604 fix requires for windows 2024-04-03 21:56:43 +08:00
hiyouga 148bda353f fix resize vocab at inference #3022 2024-04-03 18:14:24 +08:00
hiyouga ce77d98872 fix #3116 2024-04-03 14:47:59 +08:00
hiyouga 92dab8a90b simplify readme 2024-04-02 20:07:43 +08:00
hiyouga b267aeb53f add moe aux loss control #3085 2024-04-02 14:26:31 +08:00
hiyouga 9ddbe2866a fix #3022 2024-04-02 13:58:39 +08:00
hiyouga dd73a0c248 set dev version 2024-04-01 23:24:08 +08:00
hiyouga 4a6ca621c0 fix #3083 2024-04-01 22:53:52 +08:00
hiyouga 54b7d34908 add qwen1.5 moe 2024-04-01 21:49:40 +08:00
hiyouga aee634cd20 fix #3077 2024-04-01 21:35:18 +08:00
hiyouga eb259cc573 support infer 4bit model on GPUs #3023 2024-04-01 17:34:04 +08:00
hiyouga d0842f6828 update webui 2024-04-01 16:23:28 +08:00
hiyouga 816d714146 fix ORPO loss 2024-04-01 14:42:41 +08:00
hiyouga 5b9b40403d fix IPO and ORPO loss 2024-04-01 14:37:53 +08:00
hiyouga 5907216a1c fix plots 2024-03-31 19:43:48 +08:00
hiyouga 68aaa4904b use log1p in orpo loss 
https://github.com/huggingface/trl/pull/1491
 2024-03-31 19:27:08 +08:00
hiyouga 099db6acc0 update readme 2024-03-31 18:46:34 +08:00
hiyouga 5195add324 support orpo in webui 2024-03-31 18:34:59 +08:00
hiyouga 17bf8a2c3a support ORPO 2024-03-31 18:29:50 +08:00
hiyouga 27776c3474 tiny fix 2024-03-31 00:10:29 +08:00
marko1616 d9a5134617 fix blank line contains whitespace 2024-03-30 23:46:55 +08:00
marko1616 eb178eaff3 Fix Llama model save for full param train 2024-03-30 23:45:04 +08:00