Deploy Dedicated GPU server to run AI models

Deploy Model
Skip to main content
SlimTurbo LoRA 8 Step - BF16 Decomp thumbnail

SlimTurbo LoRA 8 Step - BF16 Decomp API Documentation

by ModelsLab

Decomposed the lora_a and lora_b into one. Now it's 150mb but I'm not sure that it's as good. Gens seem to have less detail.

slimturbo-lora-8-step-bf16-decomp
Open Source ModelUnlimited UsageLLMs.txt
API PlaygroundAPI Documentation