How to use mutaician/nllb-swahili-kalenjin-v3 with PEFT:
from peft import PeftModel from transformers import AutoModelForSeq2SeqLM base_model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-600M") model = PeftModel.from_pretrained(base_model, "mutaician/nllb-swahili-kalenjin-v3")
How to use mutaician/nllb-swahili-kalenjin-v3 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="mutaician/nllb-swahili-kalenjin-v3")
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mutaician/nllb-swahili-kalenjin-v3", dtype="auto")
