MiniCPM-1B-SFT
MiniCPM-1B-SFT is an AI model published by OpenBMB, released on 2024-04-10, for 基础大模型, with 12.0B parameters, and 4K tokens context length, requiring about 2.72GB storage, under the OpenBMB通用模型许可协议-来源说明-宣传限制-商业授权 license.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
面壁智能开源的12亿参数规模的大语言模型，官方宣称其评测结果与70亿参数规模的大模型接近。
MiniCPM系列模型的参数规模都不超过30亿（不包含MiniCPM-8×2B-MoE，这个136亿，参考： https://www.datalearner.com/ai-models/pretrained-models/MiniCPM-MoE-8x2B ），因此推理显存要求很低，微调也仅需一个消费级显卡即可：
欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送
