shuxueslpi/chatGLM-6B-QLoRA
使用peft库,对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调,并做lora model和base model的merge及4bit的量化(quantize)。
Python
Stargazers
- 413622944
- AdamBear
- azoth07
- berton820
- ChanChiChoiChina
- chenpythonChongQing
- choupw
- cxy8520
- dengguanguan
- fjw1049
- Gowott
- GXKIM
- HongyuJiangSalari-man
- huangbaichaoChina
- Huanghaonan88
- intellecatCatЯun
- liujun2Beijing
- NileZhouByteDance Ltd. alum
- QingqingSun-Bao
- RanchiZhaoModelBest
- ranchlaiPA group
- ricklttGuangdong University of Technology
- RunchenSong
- ShayDuaneBeijing,China
- shuxueslpinanjing
- sinnammJiNan, China
- sunxs1101
- sunyui
- svjack
- TechWithRayGoogle
- teouueteouue
- tfdetang
- ThreeStonesSL
- tongxuluo
- woshiluoming
- zhuyuan2016