albertvillanova/legal_contracts
Viewer • Updated • 106k • 329 • 50
How to use muhtasham/bert-small-finetuned-legal-contracts-larger20-5-1 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("fill-mask", model="muhtasham/bert-small-finetuned-legal-contracts-larger20-5-1") # Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("muhtasham/bert-small-finetuned-legal-contracts-larger20-5-1")
model = AutoModelForMaskedLM.from_pretrained("muhtasham/bert-small-finetuned-legal-contracts-larger20-5-1")This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the portion of legal_contracts dataset for 1 epoch.
The model was not trained on the whole dataset which is around 9.5 GB, but only
train + the last 5% of train.
datasets_train = load_dataset('albertvillanova/legal_contracts' , split='train[:20%]')
datasets_validation = load_dataset('albertvillanova/legal_contracts' , split='train[-5%:]')