alpaca-13b-hf-int4 / README.md
nealchandra's picture
Update README.md
b3e213c
metadata
license: other
datasets:
  - tatsu-lab/alpaca

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.