# Multi-task pre-training

This is an Indonesian text embedding model based on sentence-transformers, capable of mapping sentences and paragraphs into a 384-dimensional dense vector space, suitable for tasks such as clustering and semantic search.

InCaseLawBERT is a BERT model pre-trained on Indian legal texts, focusing on natural language processing tasks related to Indian law.

UniSpeech is a unified speech representation learning model that combines labeled and unlabeled data for pre-training, specifically fine-tuned for French.

UniSpeech is a unified speech representation learning model that combines supervised phoneme CTC learning and self-supervised learning, specifically fine-tuned for Italian.

Go language code documentation generation model based on T5-small architecture, supporting multi-task processing

Pre-trained model based on T5-large architecture, specifically designed for generating Java function/method code comment documentation

A Java code documentation generation model based on the T5 large architecture, supporting multi-task training and excelling in generating Java function descriptions

A multi-task pre-trained model based on T5 small architecture, specializing in generating API usage suggestions for Java programming tasks

Java code comment generation model based on T5-small architecture, supporting multi-task training, suitable for automatic Java function documentation generation

A pre-trained model based on the T5 architecture, specifically designed for generating Java function documentation with multi-task processing support

A Python code documentation generation model based on T5 architecture, pre-trained and fine-tuned with multi-task learning, specifically designed for generating Python function documentation

A T5 architecture-based Go language code documentation generation model, pre-trained and fine-tuned with multi-task learning, specifically designed for generating documentation for Go functions/methods.

A Java code comment generation model based on the T5 architecture, optimized through multi-task pre-training and fine-tuning, specifically designed to generate descriptive text for Java functions.