T-LLaMA is a Tibetan large language model trained on the LLaMA2-7B model, constructed with a corpus containing 2.2 billion Tibetan characters, demonstrating excellent performance in text classification, generation, and summarization tasks.

Natural Language ProcessingTransformersOther

This model is based on the LaBSE framework and supports sentence similarity calculation in multiple languages (including Tibetan, Buddhist Chinese, Sanskrit, and Pali), primarily used for information retrieval and bilingual text alignment tasks.

Natural Language ProcessingTransformers

This is a Tibetan pre-trained causal language model based on the RoBERTa architecture, primarily designed for Tibetan text generation tasks.

Natural Language ProcessingTransformersOther