A repository to run gpt-j-6b on low vram machines (4.2 gb minimum vram for 2000 token context, 3.5 gb for 1000 token context). Model loading takes 12gb free ram.
Apache License 2.0
114
stars
12
forks
source link
Make it work with the latest version of transformers #1
arrmansa
commented
3 years ago
There are speedups and memory savings implemented in the latest version.