SambaLingo-Thai-Base-70B is a pretrained Bi-lingual Thai and English model that adapts Llama-2-70b to Thai by training on 26 billion tokens from the Thai split of the Cultura-X dataset. This model reports state of the art evaluation results in perplexity and FLORES-200 translation. For the chat version of this model, please see sambanovasystems/SambaLingo-Thai-Chat-70B, or try it out at SambaLingo-chat-space. — Developed by: SambaNova Systems — Model type: Language Model — Language(s): Thai, English — Finetuned from model: Llama-2-70b — Paper: SambaLingo: Teaching Large Language Models New Languages — Blog Post: sambalingo-open-source-language-experts We suggest setting do_sample=False as this is a pretrained checkpoint. This model is a pretrained checkpoint, so to use it effectively please use few shot prompting with exemplars. The only other prompt templating required is the standard (BOS) token from the Llama tokenizer. If you want to interact with this model with direct questions or queries, please use the chat version of the model that has been aligned with human preferences sambanovasystems/SambaLingo-Thai-Chat-70B. All pre-training is done on the Cultura-X dataset. We mix…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: sambanovasystems
Теги: llama, th, en, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 41
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
