phi-3-small 7.4B

Training compute

2.1×10²³ FLOP

Parameters

7.4B

Published

Apr 23, 2024

phi-3-small 7.4B is an AI model developed by Microsoft (United States), first published in April 2024. It works in the language domain, on tasks such as chat and language modeling/generation.

Training it took an estimated 2.1×10²³ FLOP of compute (estimation method: operation counting). The model has 7,400,000,000 parameters. It was trained on roughly 4.8T datapoints.

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

Full record

Organization: Microsoft
Country of organization: United States
Domain: Language
Task: Chat, Language modeling/generation
Training compute: 2.1×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 7,400,000,000
Dataset size: 4.8T
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident

Benchmark results

01

Epoch Capabilities Index

ECI Score

121.6