Hunyuan-Large

model paper
Tencent
Open-source MoE model with 52B activated parameters out of 389B total. 256K context. Pre-trained on 7T tokens.
GitHubHuggingFacePaper (arXiv)

Outputs 2

Hunyuan-Large

model
GitHubHuggingFace
Architecture MOE
Parameters 389B
Active params 52B
Context window 256,000
Training tokens 7T

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters

paper
Paper (arXiv)
Citations 5
arXiv HTML
moeopen-weightfrontier