European Open Source AI Index
DatabaseNewsGuidesAboutContribute

Stanford Alpaca

by Stanford University CRFM

Very early open-source LLM.
Text
Full
https://crfm.stanford.edu/2023/03/13/alpaca.html
Llama-7B
Alpaca-7B
LLaMA license agreement
Stanford University's Centre for Research on Foundation Models.
https://crfm.stanford.edu/
March 2023
Availability
Base Model Data
Based on LLaMA, whose pretraining data is nowhere disclosed or documented.
End User Model Data
alpaca_data.json contains 52K instruction-following data we used for fine-tuning the Alpaca model.
https://github.com/tatsu-lab/stanford_alpaca#data-release
Base Model Weights
LLaMA 1 based, copyright status unclear.
End User Model Weights
LLaMA 1 based, so weights are published through a diff.
https://github.com/tatsu-lab/stanford_alpaca#data-release
Training Code
Training code documented in repo.
https://github.com/tatsu-lab/stanford_alpaca?tab=readme-ov-file#fine-tuning
Documentation
Code Documentation
Insofar as code is made available it is fairly well documented.
https://github.com/tatsu-lab/stanford_alpaca
Hardware Architecture
Fair bit of documentation available on github repository.
https://github.com/tatsu-lab/stanford_alpaca#fine-tuning
Preprint
No preprint found; uses the release-by-blogpost playbook.
https://crfm.stanford.edu/2023/03/13/alpaca.html
Paper
No peer-reviewed paper found.
Modelcard
No model card found.
Datasheet
No data sheet found.
Access
Licenses
Pegged to LLaMA license agreement.
https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform
Last updated 13 March 2026
Is this information not up to date?
Contribute here ->
Supported by the Centre for Language Studies and the Dutch Research Council. Website design & development © 2024 by BSTN. This version of the index generated 09 April 2026, website content last updated 11 March 2026.