Under the hood

Getting LLaMA 2 able to launch required a number of tweaking to make the model safer and fewer more likely to spew toxic falsehoods than its predecessor, Al-Dahle says. 

Meta has loads of past gaffes to learn from. Its language model for science, Galactica, was taken offline after only three days, and its previous LlaMA model, which was meant just for research purposes, was leaked online, sparking criticism from politicians who questioned whether Meta was taking proper account of the risks related to AI language models, corresponding to disinformation and harassment. 

To mitigate the danger of repeating these mistakes, Meta applied a combination of various machine learning techniques geared toward improving helpfulness and safety. 

Meta’s approach to training LLaMA 2 had more steps than usual for generative AI models, says Sasha Luccioni, a researcher at AI startup Hugging Face. 

The model was trained on 40% more data than its predecessor. Al-Dahle says there have been two sources of coaching data: data that was scraped online, and a knowledge set fine-tuned and tweaked in line with feedback from human annotators to behave in a more desirable way. The corporate says it didn’t use Meta user data in LLaMA 2, and excluded data from sites it knew had plenty of personal information. 

Despite that, LLaMA 2 still spews offensive, harmful, and otherwise problematic language, similar to rival models. Meta says it didn’t remove toxic data from the information set, because leaving it in might help LLaMA 2 detect hate speech higher, and removing it could risk by chance filtering out some demographic groups.  

Nevertheless, Meta’s commitment to openness is exciting, says Luccioni, since it allows researchers like herself to review AI models’ biases, ethics, and efficiency properly. 

The indisputable fact that LLaMA 2 is an open-source model can even allow external researchers and developers to probe it for security flaws, which can make it safer than proprietary models, Al-Dahle says. 

Liang agrees. “I’m very excited to try things out and I feel it can be helpful for the community,” he says.