Unverified85% confidenceFactTime unknown
豆包大模型是字节跳动自研的通用大语言模型，基于Transformer架构训练，在中文理解和生成任务上针对国内用户场景进行了专项优化
1
Sources
85%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedByteDance's Doubao large model is based on the self-developed Skylark foundation model and belongs to the category of large language models with hundreds of billions of parameters.73% similarUnverified主流大语言模型基于Transformer架构，通过预训练将知识压缩进数十亿乃至数千亿的模型权重中72% similarUnverifiedThe Spark large model integrates iFLYTEK's accumulated capabilities in speech recognition and Chinese educational corpora, with targeted optimization for Chinese language and oral evaluation scenarios.72% similarUnverifiedTongyi Lingma is based on Alibaba's Tongyi Qianwen large model and has been specifically optimized for Chinese development scenarios and commonly used domestic technology stacks.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/7018API
curl https://kongchang.com/api/v1/knowledge/claims/7018MCP
get_claim(id=7018)