MiniCPM-1.2B

Training compute

7.9×10²¹ FLOP

Parameters

1.2B

Published

Jun 3, 2024

MiniCPM-1.2B is an AI model developed by Tsinghua University and ModelBest (China), first published in June 2024. It works in the language domain, on tasks such as language modeling/generation, code generation and translation.

Training it took an estimated 7.9×10²¹ FLOP of compute (estimation method: operation counting). The model has 1,247,442,432 parameters.

Access: Open weights (restricted use). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Tsinghua University, ModelBest
Country of organization: China
Domain: Language
Task: Language modeling/generation, Code generation, Translation
Training compute: 7.9×10²¹ FLOP
Compute estimation method: Operation counting
Parameters: 1,247,442,432
Model accessibility: Open weights (restricted use)
Open weights: Yes
Epoch confidence: Confident