teodor98's picture
Update README
eb40e7c
|
raw
history blame contribute delete
No virus
260 Bytes
metadata
license: llama2
language:
  - bg

This model is being trained with help of LORA technique on Bulgarian data from: https://www.kaggle.com/datasets/auhide/bulgarian-recipes-dataset/

This LLAMA version is 4bit encoded version of the 16bit LLAMA 2 7B model.