How to use asas-ai/opus-mt-ar-en-finetuned_augmented_MT-ar-to-en 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="asas-ai/opus-mt-ar-en-finetuned_augmented_MT-ar-to-en")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("asas-ai/opus-mt-ar-en-finetuned_augmented_MT-ar-to-en") model = AutoModelForSeq2SeqLM.from_pretrained("asas-ai/opus-mt-ar-en-finetuned_augmented_MT-ar-to-en", device_map="auto")
https://huggingface.co/asas-ai/opus-mt-ar-en-finetuned_augmented_MT-ar-to-en/resolve/main/special_tokens_map.json
hf download hf://asas-ai/opus-mt-ar-en-finetuned_augmented_MT-ar-to-en/special_tokens_map.json
curl -L -o special_tokens_map.json https://huggingface.co/asas-ai/opus-mt-ar-en-finetuned_augmented_MT-ar-to-en/resolve/main/special_tokens_map.json
