LLaMA (Large Language Model Meta AI) is a large language model released by Meta AI in February 2023. It is a foundational model with 65 billion parameters and is more efficient and competitive than previous models. LLaMA was created to help researchers and was released as an open-source package that anyone in the AI community can request access to. The intention behind this was to “further democratize access” to AI and spur research into its problems
LLaMA (Large Language Model Meta AI) is a large language model released by Meta AI in February 2023. It is a foundational model with 65 billion parameters and is more efficient and competitive than previous models. LLaMA was created to help researchers and was released as an open-source package that anyone in the AI community can request access to. The intention behind this was to “further democratize access” to AI and spur research into its problems.
LLaMA is not a single system but four models of differing sizes and computational demands. The largest model is competitive with state-of-the-art models such as PaLM and Chinchilla. The 13 billion parameter model’s performance on most NLP benchmarks exceeded that of the much larger GPT-3 (with 175 billion parameters).
LLaMA was announced on February 23, 2023, via a blog post and a paper describing the model’s training, architecture, and performance. The code used to train the model was publicly released under the open-source GPL 3 license. Access to the model’s weights was managed by an application process, with access to be granted “on a case-by-case basis to academic researchers; those affiliated with organizations in government, civil society, and academia”.
On April 17, 2023, Together launched a project named RedPajama to reproduce LLaMA’s results. However, LLaMA was leaked on 4chan a week after it was announced, raising concerns about its potential misuse. Meta did not release LLaMA as a public chatbot, but rather as an AI system that needs a decent amount of technical expertise to get up and running.
On July 18, 2023, Meta and Microsoft introduced the availability of Llama 2, the next generation of their open-source large language model. Facebook parent company Meta Platforms has also built an artificial intelligence system that rivals the likes of ChatGPT and Google’s Bard.
In summary, LLaMA is a large language model released by Meta AI in February 2023. It is a foundational model with 65 billion parameters and is more efficient and competitive than previous models. LLaMA was created to help researchers and was released as an open-source package that anyone in the AI community can request access to. Access to the model’s weights was managed by an application process. LLaMA was leaked on 4chan a week after it was announced, raising concerns about its potential misuse.
