LLaMA vs. RedPajama-INCITE

Overview

LLaMA was previously Meta AI's most performant LLM available for researchers and noncommercial use cases. It has since been succeeded by Llama 2.

The model that launched a frenzy in open-source instruct-finetuned models, LLaMA is Meta AI's more parameter-efficient, open alternative to large commercial LLMs. Despite being smaller than many commercial models, LLaMA outperformed the gold standard GPT-3 on many benchmarks, with the primary drawback being that its access remains gated to researchers with restrictions on commercial use.

Initial release: 2023-02-24

Reference

https://ai.facebook.com/blog/large-language-model-llama-meta-ai/

Further Reading

• https://arxiv.org/abs/2302.13971

Overview

RedPajama-INCITE is the first family of models trained on the RedPajama base dataset. The goal of the RedPajama-INCITE models is to replicate the LLaMA recipe but make the model fully open source under the Apache license. As of the initial release, the 3B parameter model is best-in-class, with the 7B parameter model in progress. Update as of June 6, 2023: the 7B parameter model was made available, outperforming other models of the same size.

Initial release: 2023-05-05

Reference

https://www.together.xyz/blog/redpajama-models-v1

Further Reading

• https://www.together.xyz/blog/redpajama-7b