Engine-XL(NE)

Parameters

1.5B

Published

Dec 11, 2021

Engine-XL(NE) is an AI model developed by Boston University (United States), first published in December 2021. It works in the language, vision and multimodal domain, on tasks such as named entity recognition (ner).

Epoch AI has no training-compute estimate for this model. The model has 1,500,000,000 parameters. It was trained on roughly 602.9M datapoints.

Access: Open weights (unrestricted). Its weights are openly available. It is built on top of GPT-2 (1.5B). The reference paper has 3 citations.

Full record

Organization: Boston University
Country of organization: United States
Domain: Language, Vision, Multimodal
Task: Named entity recognition (NER)
Parameters: 1,500,000,000
Dataset size: 602.9M
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Base model: GPT-2 (1.5B)
Citations: 3