Zamba2-7B

Training compute

8.8×10²² FLOP

Parameters

7B

Published

May 26, 2024

Zamba2-7B is an AI model developed by Zyphra (United States), first published in May 2024. It works in the language domain, on tasks such as language modeling/generation, chat, text summarization and 2 more.

Training it took an estimated 8.8×10²² FLOP of compute (estimation method: operation counting). The model has 7,000,000,000 parameters. Training ran on 128 NVIDIA H100 SXM5 80GB.

Access: Open weights (unrestricted). Its weights are openly available. It is built on top of Mamba 2, 2.7B. The reference paper has 112 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Zyphra
Country of organization: United States
Domain: Language
Task: Language modeling/generation, Chat, Text summarization, Code generation, Question answering
Training compute: 8.8×10²² FLOP
Compute estimation method: Operation counting
Parameters: 7,000,000,000
Training hardware: NVIDIA H100 SXM5 80GB
Chips used: 128
Training power draw: 177.0 kW
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Base model: Mamba 2, 2.7B
Citations: 112
Epoch confidence: Confident