The Local LLM Index / Quantization & Formats / #18
MakazhanAlpamys/Soup
by MakazhanAlpamys · Quantization & Formats · updated today
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
75
momentum
6,176
stars
953
forks
#18
rank
cliconsumer-gpudpofine-tuningggufhuggingfacellmllmopslocal-ailocal-llmloralow-vram
View on GitHub →