Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · nlpaueb

bert-base-uncased-contracts

bert-base-uncased-contracts is a LEGAL-BERT contracts variant from nlpaueb. According to the model card, it is pre-trained on US contracts for legal masked-language modeling.

Publisher
nlpaueb
Task
fill-mask
Model type
bert
License
cc-by-sa-4.0
Library
transformers
Publication status
Accepted · not indexed

Model overview

bert-base-uncased-contracts is published by nlpaueb as a BERT fill-mask model. According to the model card, it is the CONTRACTS-BERT-BASE sub-domain variant pre-trained on US contracts within the LEGAL-BERT family. The card describes a BERT-BASE configuration with 110M parameters, and card data records cc-by-sa-4.0.

Recorded capabilities

Contracts sub-domain specialization

According to the model card, this checkpoint is the CONTRACTS-BERT-BASE variant trained on US contracts within the broader LEGAL-BERT family.

BERT-BASE legal configuration

According to the model card, the model follows the 12-layer, 768-hidden, 12-head, 110M-parameter BERT-BASE setup using the official Google BERT code.

CC-BY-SA-4.0 legal-domain record

Card data records cc-by-sa-4.0, and hub tags mark legal-domain fill-mask use with English support.

Documented masked-language use

According to the model card, the publisher shows loading the model with AutoTokenizer and AutoModel for masked-token prediction on contract text.

Use cases in the source record

  • Legal-domain masked-language modeling on contracts text using the documented fill-mask setup.
  • Legal NLP research and computational-law experiments assisted by a contracts-specialized BERT variant.

Limitations and unknowns

  • No Safetensors parameter count was extracted from this record; the 110M figure is a publisher model-card claim.
  • No evaluation results were extracted from this record.
  • No context-window value was extracted from this record.
  • Provider state is historical snapshot data and should be refreshed before being presented as current.

Source and provenance

Source: nlpaueb/bert-base-uncased-contracts

Captured: Unknown. Processed: 2026-09-07T19:34:53.498017+00:00.

LEGAL-BERT: The Muppets straight out of Law School LEGAL-BERT is a family of BERT models for the legal domain, intended to assist legal NLP research, computational law, and legal technology applications. To pre-train the different variations of LEGAL-BERT, we collected 12 GB of diverse English legal text from several fields (e.g., legislation, court cases, contracts) scraped from publicly available resources. Sub-domain variants (CONTRACTS-, EURLEX-, ECHR-) and/or general LEGAL-BERT perform better than using BERT out of the box for domain-specific tasks. This is the sub-domain variant pre-trained on US contracts. I. Chalkidis, M. Fe…

F001F002F003F004F005F007F008F009F010F013F014F016F017