SGPT BE 5.8B

Parameters

5.8B

Published

Aug 5, 2022

SGPT BE 5.8B is an AI model developed by Peking University (China), first published in August 2022. It works in the language domain, on tasks such as semantic search, semantic embedding and entity embedding.

Epoch AI has no training-compute estimate for this model. The model has 5,800,000,000 parameters. Training ran on 8 NVIDIA A100 SXM4 40 GB for about 60 hours.

Access: Open weights (non-commercial). Its weights are openly available. It is built on top of GPT-J-6B. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Peking University
Country of organization: China
Domain: Language
Task: Semantic search, Semantic embedding, Entity embedding
Compute estimation method: Hardware
Parameters: 5,800,000,000
Training hardware: NVIDIA A100 SXM4 40 GB
Chips used: 8
Training time: 60 h
Training power draw: 6.4 kW
Model accessibility: Open weights (non-commercial)
Open weights: Yes
Base model: GPT-J-6B
Epoch confidence: Confident