Llama 2

Llama 2 is an open source large language model developed by Meta AI. Llama 2 is now available for free for both research and commercial use. This innovative model comes with pretrained and fine-tuned language models, ranging from 7B to 70B parameters, providing enhanced context length compared to its predecessor, Llama 1. Llama 2's pretrained models have been trained on an impressive 2 trillion tokens and its fine-tuned models have undergone rigorous training with over 1 million human annotations. Outperforming other open source language models, Llama 2 excels in various areas including reasoning, coding proficiency, and knowledge tests.