abhibisht89
commented
3 years ago @Peter857 you can give is as dmis-lab/biobert-base-cased-v1.1 \, it will work
python run_ner.py \ --data_dir ${DATA_DIR}/${ENTITY} \ --labels ${DATA_DIR}/${ENTITY}/labels.txt \ --model_name_or_path dmis-lab/biobert-base-cased-v1.1 \ --output_dir output/${ENTITY} \ --max_seq_length 128 \ --num_train_epochs 30 \ --per_device_train_batch_size 32 \ --save_steps 1000 \ --seed 1 \ --do_train \ --do_eval \ --do_predict \ --overwrite_output_dir
Hello, I have been looking at the content of Biobert recently, and I want to fine-tune Biobert, but during the process, how to fill in model_name_or_path. Are there any questions about the following? : model_name_or_path: str = field( metadata={"dmis-lab/biobert-base-cased-v1.1": "Path to pretrained model or model identifier from huggingface.co/models"} ) Hope to get your answer, thank you