TinyLlama-1.1B — это компактная языковая модель, обученная на колоссальном объеме в 1 триллион токенов. Благодаря архитектуре Llama 2 и оптимизациям FlashAttention, этот ИИ демонстрирует отличную производительность в задачах генерации текста, работая даже на устройствах с ограниченными ресурсами.
We present TinyLlama, a compact 1.1B language model pretrained on around 1 trillion tokens for approximately 3 epochs. Building on the architecture and tokenizer of Llama 2, TinyLlama leverages various advances contributed by the open-source community (e.g., FlashAttention), achieving better computational efficiency. Despite its relatively small size, TinyLlama demonstrates remarkable performance in a series of downstream tasks. It significantly outperforms existing open-source language models with comparable sizes. Our model checkpoints and code are publicly available on GitHub at https://github.com/jzhang38/TinyLlama