LLaMA

From
Revision as of 21:05, 21 July 2023 by BPeat (talk | contribs)
Jump to: navigation, search

YouTube search... ...Google search

LLaMA is a Large Language Model (LLM) released by Meta Platforms Inc. (formerly Facebook Inc.).

LLaMA 2

Meta released LLaMA in July 2023. The company said that it hopes that by making LLaMA open-source, it will be able to improve the model by getting feedback from the wider community of developers. LLaMA is still under development, but it has already been used to create some impressive chatbots. For example, one chatbot called Allie can be used to provide customer support. Another chatbot called Galactica is designed for scientific research.

LLaMA

LLaMA on February 24, 20231. Meta says it is democratizing access to LLMs, which are seen as one of the most important and beneficial forms of AI. The four foundation models of LLaMA are LLaMA-7B, LLaMA-13B, LLaMA-33B, and LLaMA-65B12. They have 7 billion, 13 billion, 33 billion, and 65 billion parameters respectively. The models are all based on the transformer architecture and trained on publicly available datasets. LLaMA-13B is remarkable because it can run on a single GPU and outperform GPT-3 (175 billion parameters) on most common sense reasoning benchmarks. LLaMA-65B is competitive with the best models from other AI labs, such as Chinchilla 70B and PaLM 540B.