Palmyra Large 20B

Training compute

9.6×10²² FLOP

Parameters

20B

Published

Mar 1, 2023

Palmyra Large 20B is an AI model developed by Writer (United States), first published in March 2023. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 9.6×10²² FLOP of compute (estimation method: operation counting). The model has 20,000,000,000 parameters. It was trained on roughly 800B datapoints.

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

Full record

Organization: Writer
Country of organization: United States
Domain: Language
Task: Language modeling
Training compute: 9.6×10²² FLOP
Compute estimation method: Operation counting
Parameters: 20,000,000,000
Dataset size: 800B
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Speculative