britllm/TransWebLLM-web

This is a raw, pretrained multilingual language model, supporting Arabic, Welsh, German, English, Spanish, French, Indonesian, Italian, Russian, and Swahili. The model is pretrained from scratch, which should be further finetuned for most use cases.

For more details: Multilingual Language Model Pretraining using Machine-translated Data

Contact Email: jiaywang@cs.ucl.ac.uk