How to use KETI-AIR-Downstream/long-ke-t5-base-translation-aihub-bidirection_e1 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="KETI-AIR-Downstream/long-ke-t5-base-translation-aihub-bidirection_e1")
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("KETI-AIR-Downstream/long-ke-t5-base-translation-aihub-bidirection_e1") model = AutoModelForSeq2SeqLM.from_pretrained("KETI-AIR-Downstream/long-ke-t5-base-translation-aihub-bidirection_e1", device_map="auto")
https://huggingface.co/KETI-AIR-Downstream/long-ke-t5-base-translation-aihub-bidirection_e1/resolve/main/tokenizer.json
hf download hf://KETI-AIR-Downstream/long-ke-t5-base-translation-aihub-bidirection_e1/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/KETI-AIR-Downstream/long-ke-t5-base-translation-aihub-bidirection_e1/resolve/main/tokenizer.json
