LLaMA model finetuned using LoRA (1 epoch) on the Stanford Alpaca training data set and quantized to 4bit.
Because this model contains the merged LLaMA weights it is subject to their license restrictions.
LLaMA model finetuned using LoRA (1 epoch) on the Stanford Alpaca training data set and quantized to 4bit.
Because this model contains the merged LLaMA weights it is subject to their license restrictions.