BlueLM 7B

Training compute

1.1×10²³ FLOP

Parameters

7B

Published

Oct 31, 2023

BlueLM 7B is an AI model developed by vivo AI lab (China), first published in October 2023. It works in the language domain, on tasks such as chat, translation, language modeling/generation and 2 more.

Training it took an estimated 1.1×10²³ FLOP of compute (estimation method: operation counting). The model has 7,000,000,000 parameters. It was trained on roughly 2.6T datapoints.

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

Full record

Organization: vivo AI lab
Country of organization: China
Domain: Language
Task: Chat, Translation, Language modeling/generation, Question answering, Code generation
Training compute: 1.1×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 7,000,000,000
Dataset size: 2.6T
Model accessibility: Open weights (restricted use)
Open weights: Yes
Epoch confidence: Confident