Tag: context compression model

Context compression model explained — what it is, how it works and what it costs. Below are 1 article about context compression model on CheapToken News.

Inference costs cut by 78%, API costs cut by 97%: Peking University-affiliated startup open-sources a 4B context compression model

March 19, 2018 | 智东西
Inference costs cut by 78%, API costs cut by 97%: Peking University-affiliated startup open-sources a 4B context compression model
Zhidx (WeChat official account: zhidxcom) Author | Yang Jingli Editor | Li Shuiqing Zhidx reported on November 11 that today, Silicon Heart Technology (aiXcoder), an AI coding startup incubated by the Institute of Software Engineering at Peking University, open-sourcedthe context compression model aiXcompact-4B. The model is designed primarily for long-horizon, complex R&D tasks involving coding agents, has only4B parameters, andsupports private deployment

Related articles