starlight-apk/Qwen
1
0
Fork 0
mirror of https://github.com/QwenLM/Qwen.git synced 2026-05-21 00:45:48 +08:00
Code Issues Packages Projects Releases Wiki Activity
435 Commits 25 Branches 0 Tags
4aab1d490b268783bdda80b87b7fb501539b7929
Commit Graph

14 Commits

Author SHA1 Message Date
Ren Xuancheng
a6c1ea82ba Remove redundant code in finetune.py 
Fix https://github.com/QwenLM/Qwen/issues/660
 2023-11-30 19:21:06 +08:00
Ren Xuancheng
8c7174e8c0 fix typo in finetune.py 
fix https://github.com/QwenLM/Qwen/issues/687
 2023-11-30 17:54:04 +08:00
yangapku
e8e15962d8 add 72B and 1.8B Qwen models, add Ascend 910 and Hygon DCU support, add docker support 2023-11-30 15:29:13 +08:00
yangapku
981c89b2a9 update finetune.py 2023-11-14 18:22:06 +08:00
Junyang Lin
daf00604d9 Update finetune.py 2023-10-25 12:05:21 +08:00
songt
e46d65084a print peft trainable params 2023-10-20 17:38:47 +08:00
Junyang Lin
3e63f107fa Update finetune.py 2023-10-20 13:22:11 +08:00
梦典
f3d7c69be2 Update finetune.py 
Just lora finetuing need low cpu memory usage
 2023-10-18 15:24:45 +08:00
梦典
67b3f949b6 Update finetune.py For lower cpu memory 
1.Change default device_map to "auto"
device_map = "auto"
2.For lower cpu memory, add parameter at load model
low_cpu_mem_usage=True,
 2023-10-16 16:13:10 +08:00
Junyang Lin
00dceebbaa Update finetune.py 2023-10-09 01:11:24 +08:00
Junyang Lin
f7681f9e77 Update finetune.py 2023-10-07 18:47:29 +08:00
Junyang Lin
75cc160f74 Update finetune.py 2023-10-07 14:49:44 +08:00
JustinLin610
b5fad3d561 fix single-gpu qlora, and add profiling 2023-10-07 10:37:42 +08:00
JustinLin610
af22d5e0ce add finetuning 2023-09-11 23:47:32 +08:00