This is a static quantized version of the moka-ai/m3e-base model, specifically designed for text embedding tasks and supporting both Chinese and English. It offers a variety of quantization levels, from Q2_K to f16, to meet the performance and accuracy requirements of different scenarios.

Natural Language ProcessingTransformersMultiple Languages

This is a statically quantized version of the ltg/flan-t5-definition-en-xl base model, specifically designed for text-to-text generation and definition modeling tasks. The model offers multiple quantization levels, ranging from the tiny Q2_K to the high-quality Q8_0 and f16 versions. Users can choose the appropriate version based on their hardware resources and precision requirements.

Natural Language ProcessingTransformersEnglish

This is a deep learning model specifically designed to recognize puns in Portuguese texts. It is fine-tuned on the Puntuguese dataset based on the BERT architecture and has achieved an excellent performance with a 69% F1 score in the pun recognition task.

Natural Language ProcessingSafetensorsOther

This is a deep - learning model focused on image classification tasks, using accuracy, recall, and F1 score as the main evaluation metrics, and following the Apache 2.0 open - source license.

Computer VisionTransformers

This model is a fine-tuned version of facebook/levit-192 on an unlabeled dataset, demonstrating excellent performance in precision, recall, F1 score, and accuracy.

Computer VisionTransformers

This is an Indian legal named entity recognition model trained based on the spaCy framework. It is specifically designed to identify various legal entities in Indian legal judgment texts and achieved an F1 score of 91.076 in testing. It supports the recognition of 14 types of legal entities.

Natural Language ProcessingSpacyEnglish

A deep learning-based text classification model that demonstrates high F1 score and ROC AUC values on the validation set.

Natural Language ProcessingTransformers