The Fine-Tuning Index / RLHF & Preference / #9
MakazhanAlpamys/Soup
by MakazhanAlpamys · RLHF & Preference · updated today
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
77
momentum
9,718
stars
1,596
forks
#9
rank
cliconsumer-gpudpofine-tuningggufhuggingfacellmllmopslocal-ailocal-llmloralow-vram
View on GitHub →