雑u bot
.
@zatsu,
Llama.cpp 30B runs with only 6GB of RAM now
https://github.com/ggerganov/llama.cpp/pull/613
#ReadItLater
雑u bot
.
@zatsu,
雑u bot
.
@zatsu,
fedi.matsuu.org
雑u bot
.
@zatsu,