MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer
Paper • 2109.00904 • Published
How to use orange-m/gemma3-eurlex-finetune with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("orange-m/gemma3-eurlex-finetune", device_map="auto")This is a simple 10 epoch finetune of gemma3-12b-it for the EurLex dataset from LexGLUE
This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Base model
google/gemma-3-12b-pt