# Legal Text Processing

This model is a fine-tuned version of nlpaueb/legal-bert-base-uncased on the InLegalNER dataset, specifically designed for named entity recognition tasks in Indian legal texts.

This is a Portuguese instruction-tuned model based on Microsoft Phi-3-mini-4k-instruct, converted to GGUF format for use with llama.cpp.

EUBERT is a multilingual BERT model trained on documents from the European Publications Office, supporting 24 EU languages, suitable for text classification, question answering, and language understanding tasks.

A long-text legal language model based on the LexLM (Base Version) RoBERTa model, optimized for processing long legal documents

BART is a Transformer model with an encoder-decoder architecture, fine-tuned for abstractive summarization tasks of terms of service

This model is a fine-tuned T5-small model based on the HUPD dataset, specifically designed for patent text summarization tasks.

A long-document encoder-decoder (LED) model fine-tuned on the Billsum dataset, specializing in legal text summarization

This is a Named Entity Recognition (NER) model for the Portuguese legal domain, fine-tuned based on the BERT base architecture, specifically designed to identify named entities in legal texts.

A T5 model fine-tuned for German question generation tasks, trained on the GermanQUAD dataset