# Multiple sizes available

Qwen 3 is a language model based on the ExecuTorch runtime, offering both quantized and non - quantized versions of different scales.

A Chinese RoBERTa model pre-trained on CLUECorpusSmall, with a parameter scale of 8 layers and 512 hidden units.

AraGPT2 is a series of large language models pre-trained for Arabic text generation tasks, available in four sizes: base, medium, large, and mega.

This is a Chinese pre-trained language model based on the RoBERTa architecture, with a parameter scale of 8 layers and 512 hidden units, suitable for various Chinese natural language processing tasks.

A Chinese RoBERTa model pre-trained on CLUECorpusSmall, featuring 8 layers and 512-dimensional hidden layers, suitable for various Chinese NLP tasks.

AraGPT2 is a pre-trained Arabic text generation model based on the GPT2 architecture, developed by AUB MIND Lab, supporting multiple model size variants.