metadata
license: llama2
language:
- nl
LLaMA-2-NL: Fine-tuned using LoRa and the original tokenizer
from transformers import AutoModelForCausalLM, AutoTokenizer
# take the original llama 2 tokenizer
tokenizer = AutoTokenizer.from_pretrained('meta-llama/Llama-2-7b-hf')
model = AutoModelForCausalLM.from_pretrained('llama-2-nl/Llama-2-7b-hf-lora-original')