Alpaca

Parameters

7B

Published

Mar 13, 2023

Alpaca is an AI model developed by Stanford University (United States), first published in March 2023. It works in the language domain, on tasks such as language modeling/generation and question answering.

Epoch AI has no training-compute estimate for this model. The model has 7,000,000,000 parameters. Training ran on 8 NVIDIA A100 SXM4 80 GB for about 3 hours. The compute alone is estimated at $100 in 2023 dollars.

Access: Open weights (non-commercial). Its weights are openly available. It is built on top of LLaMA-7B. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Stanford University
Country of organization: United States
Domain: Language
Task: Language modeling/generation, Question answering
Compute estimation method: Hardware
Parameters: 7,000,000,000
Training hardware: NVIDIA A100 SXM4 80 GB
Chips used: 8
Training time: 3 h
Training power draw: 6.4 kW
Training cost (2023 USD): $100
Model accessibility: Open weights (non-commercial)
Open weights: Yes
Base model: LLaMA-7B
Epoch confidence: Confident