Granite 13B

Training compute

2.4×10²³ FLOP

Parameters

13B

Published

Nov 30, 2023

Granite 13B is an AI model developed by IBM (United States), first published in November 2023. It works in the language domain, on tasks such as chat, language modeling/generation, question answering and text summarization.

Training it took an estimated 2.4×10²³ FLOP of compute (estimation method: hardware,operation counting). The model has 13,000,000,000 parameters. It was trained on roughly 2.5T datapoints. Training ran on NVIDIA A100 for about 2.2K hours.

Access: API access. Its weights are not openly released. Epoch AI rates the confidence of this record as likely.

Full record

Organization: IBM
Country of organization: United States
Domain: Language
Task: Chat, Language modeling/generation, Question answering, Text summarization
Training compute: 2.4×10²³ FLOP
Compute estimation method: Hardware, Operation counting
Parameters: 13,000,000,000
Dataset size: 2.5T
Training hardware: NVIDIA A100
Training time: 2,208 h
Model accessibility: API access
Open weights: No
Epoch confidence: Likely