# Wikipedia Training

This is a LLaMA-like model with only 160 million parameters, trained on data from Wikipedia and parts of the C4-en and C4-realnewslike datasets.

This is a pre-trained Japanese ALBERT model primarily designed for fill-mask tasks, supporting Japanese text processing.

A Nordic RoBERTa model trained on Swedish, Danish, and Norwegian Wikipedia, suitable for fill-mask tasks.

A Tamil pre-trained model based on the ELECTRA framework, with the second version trained on TPUs and expanded corpus scale

Dutch Q&A model fine-tuned from Google's multilingual BERT, trained on translated SQuAD2.0 dataset

Indonesian Small RoBERTa is a masked language model based on the RoBERTa architecture, specifically trained for Indonesian language, suitable for text infilling and feature extraction tasks.

This is a French-specific version of the multilingual distilled BERT base model, retaining the original model's accuracy while being more compact.

This is a streamlined version based on bert-base-multilingual-cased, specializing in English and Spanish processing, fully reproducing the original model's representation output while maintaining its accuracy.

A Thai version customized from the multilingual distilled BERT base model, retaining the original model's accuracy and feature representation capabilities.

This is a lightweight version of distilbert-base-multilingual-cased, focused on bilingual processing of English and German, maintaining the representation capability and accuracy of the original model.

A customized lightweight language version model based on bert-base-multilingual-cased, supporting English and Thai while maintaining the original model's representation output and accuracy.

This is a compact version of the multilingual distilled BERT base model (case-sensitive), specifically optimized for Russian, capable of generating semantic representations identical to the original model while maintaining its accuracy.

This is a distilled version of distilbert-base-multilingual-cased, specifically optimized for English and Arabic processing while maintaining the original model's accuracy.

This is a compact version of distilbert-base-multilingual-cased, specifically designed for Portuguese, while maintaining the accuracy of the original model.

This is a customized distilled version of the multilingual DistilBERT base model, optimized for Vietnamese language processing while retaining the original model's representational capabilities and accuracy.

This is a streamlined version of bert-base-multilingual-cased, specifically optimized for English and Italian while retaining the original model's representational capabilities.

A streamlined Chinese BERT model customized from bert-base-multilingual-cased, supporting Chinese processing while maintaining original accuracy

This is a customized compact version of bert-base-multilingual-cased, specifically supporting English and Ukrainian processing while maintaining the original model's representation output and accuracy.