How to use ISLAM-PO/MasryGPT-Flash-Adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("aubmindlab/aragpt2-base") model = PeftModel.from_pretrained(base_model, "ISLAM-PO/MasryGPT-Flash-Adapter")
https://huggingface.co/ISLAM-PO/MasryGPT-Flash-Adapter/resolve/main/tokenizer.json
hf download hf://ISLAM-PO/MasryGPT-Flash-Adapter/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/ISLAM-PO/MasryGPT-Flash-Adapter/resolve/main/tokenizer.json
