Platypus-70B

Parameters

70B

Published

Aug 14, 2023

Platypus-70B is an AI model developed by Boston University (United States), first published in August 2023. It works in the language domain, on tasks such as language generation.

Epoch AI has no training-compute estimate for this model. The model has 70,000,000,000 parameters. Training ran on NVIDIA A100.

Access: Open weights (non-commercial). Its weights are openly available. It is built on top of Llama 2-70B. The reference paper has 187 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Boston University
Country of organization: United States
Domain: Language
Task: Language generation
Parameters: 70,000,000,000
Training hardware: NVIDIA A100
Model accessibility: Open weights (non-commercial)
Open weights: Yes
Base model: Llama 2-70B
Citations: 187
Epoch confidence: Confident