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.
Or read this on TechCrunch