# Multiple Sizes Available

OpenELM is a set of open-source efficient language models that employ a hierarchical scaling strategy to optimize parameter allocation, including pre-trained and instruction-tuned versions ranging from 270 million to 3 billion parameters.

A Chinese tokenized version of the RoBERTa medium model pre-trained on CLUECorpusSmall corpus, with tokenization processing to enhance sequence handling efficiency

PTT5 is a T5 model pretrained on the BrWac corpus, specifically optimized for Portuguese, offering multiple sizes and vocabulary choices.

A Chinese word-level RoBERTa medium model pretrained on CLUECorpusSmall, outperforming character-level models in multiple tasks

Chinese pre-trained language model based on RoBERTa architecture, with hidden layer dimension of 512 and 8 Transformer layers