liyucheng09/Selective_Context
Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.
Python
Stargazers
- badeok0716SNU CSE
- BowieHsuAlibaba
- boyuanzheng010The Ohio State University
- Chiang97912ByteDance
- Cholezlh
- CodingPeasantzglChina
- DeligneS
- endymecy@tencent
- epodak
- focuses
- ibuwei
- jacker18
- JeffCarpenterCanada
- jiashenggu
- junyz0
- jylee-mllabSNU CSE
- Kamalabot
- liyucheng09
- lwaekfjlkCKC@ZJU -> LTI@CMU -> CS@UIUC
- mrslimslim
- OmaymaS
- PenutChen
- RobbieInOz
- SamariddinSStudybook
- sep2
- SimFG
- SmileSmith@JD.com
- Totteperera
- VPeterVThe Hong Kong University of Science and Technology (HKUST)
- wktzjz
- wxingda
- xiaoxiawu-microsoft
- XrosLiang
- yqt
- zhongpei
- ZTurboX