How to use oudmaria/darija-translator with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("C:\Users\maria/.cache/huggingface/hub/models--unsloth--llama-3.2-3b-instruct-unsloth-bnb-4bit/snapshots/19846d3f624f3eb96f3bdd275620c6bc7e21e1f8") model = PeftModel.from_pretrained(base_model, "oudmaria/darija-translator")
How to use oudmaria/darija-translator with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="oudmaria/darija-translator")
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("oudmaria/darija-translator", dtype="auto")
