Get the latest tech news

Meta releases Llama 3, claims it’s among the best open models available


Meta has released several models in its new Llama 3 family, which it claims improve across the board in terms of performance versus Llama 2.

Llama 3 8B bests other open source models like Mistral’s Mistral 7B and Google’s Gemma 7B, both of which contain 7 billion parameters, on at least nine benchmarks: MMLU, ARC, DROP, GPQA (a set of biology-, physics- and chemistry-related questions), HumanEval (a code generation test), GSM-8K (math word problems), MATH (another mathematics benchmark), AGIEval (a problem-solving test set) and BIG-Bench Hard (a commonsense reasoning evaluation). Recent reporting revealed that Meta, in its quest to maintain pace with AI rivals, at one point used copyrighted ebooks for AI training despite the company’s own lawyers’ warnings; Meta and OpenAI are the subject of an ongoing lawsuit brought by authors including comedian Sarah Silverman over the vendors’ alleged unauthorized use of copyrighted data for training. “Our goal in the near future is to make Llama 3 multilingual and multimodal, have longer context and continue to improve overall performance across core [large language model] capabilities such as reasoning and coding,” Meta writes in a blog post.

Get the Android app

Or read this on TechCrunch

Read more on:

Photo of Meta

Meta

Photo of Llama 3

Llama 3

Photo of best open models

best open models

Related news:

News photo

Meta, in Its Biggest A.I. Push, Places Smart Assistants Across Its Apps

News photo

Meta rolls out an updated AI assistant, built with the long-awaited Llama 3

News photo

EU tells Meta it can't paywall privacy