LLaMA (Large Language Model Meta AI) is an open source AI model available for government, community and academic researchers and practitioners under non-commercial license. It requires “significantly less compute” than other similar products from other vendors and is available in various specifications (7B, 13B, 33B and 65B). Meta’s LLaMA offers great performance with low compute requirements, making it an ideal choice for researchers and practitioners. It has undergone training on 1 billion tokens for the smallest model LLaMA 7B and 1.4 billion tokens for the LLaMA 65B and LLaMA 33B. Performance of LLaMA is better than GPT and it can even run on a single GPU. So, if you are looking for an open source AI model with great performance and low compute requirements, LLaMA is the perfect choice.
Meta, an AI company, launched its large language model LLaMA in 2020. This model is capable of generating text in 20 languages, focusing on Latin and Cyrillic. It is multi-functional and applicable to many different use cases. Meta also provided criteria for evaluation of model bias and toxicity to ensure the model does not produce any biased or toxic comments. Additionally, Meta launched OPT-175B and Galactica, which are capable of writing scientific articles and solving math problems. Meta’s caution in launching its models is beneficial, as it helps to limit or eliminate bias, toxic comments, and illusions.
