Meta发布最新开源大模型Llama 3
可是我已不在
发表于 2024-4-19 14:39:59
218
0
0
根据Meta官方介绍,Llama 3在两个定制的24K GPU集群上基于超过15T的数据进行训练,这比Llama 2使用的数据集大7倍,代码多4倍,并且Llama 3支持8K上下文长度,是Llama 2容量的2倍。并且,Meta还放出Llama 3两个版本与谷歌Gemma、谷歌Gemini、Mistral、Anthropic的Claude 3等竞争对手的参数对比。
Meta CEO扎克伯格介绍,Meta AI将集成到Meta旗下各大产品WhatsApp、Instagram、Facebook和Messenger顶部的搜索框中,并建立一个网站meta.ai,使其更易于使用。
Meta首席科学家Yann LeCun称,未来几个月,Llama将继续推出更多版本,也将很快释放Llama 3的研究论文。英伟达高级科学家Jim Fan认为,之后可能会发布的Llama 3-400B以上版本将成为某种“分水岭”,开源社区将能用上GPT-4级别模型。
CandyLake.com is an information publishing platform and only provides information storage space services.
Disclaimer: The views expressed in this article are those of the author only, this article does not represent the position of CandyLake.com, and does not constitute advice, please treat with caution.
Disclaimer: The views expressed in this article are those of the author only, this article does not represent the position of CandyLake.com, and does not constitute advice, please treat with caution.