LLaMA Pro - 8B
LLaMA Pro - 8B is an AI model published by Tencent ARC, released on 2024-01-04, for 基础大模型, with 83.0B parameters, and 4K tokens context length, requiring about 16.72GB storage, under the Llama 2 Community License Agreement license.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
LLaMA Pro - 8B是腾讯ARC实验室提出的一种大模型微调的方法。相比较传统的有监督微调方法，这个方法可以更好地解决微调的知识遗忘问题。
相比较原始的Llama2-7B，LLaMA Pro - 8B增加了13亿的参数，但是效果好很多：
欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送
