@inproceedings{candel-etal-2023-h2o,
title = "{H}2{O} Open Ecosystem for State-of-the-art Large Language Models",
author = "Candel, Arno and
McKinney, Jon and
Singer, Philipp and
Pfeiffer, Pascal and
Jeblick, Maximilian and
Lee, Chun Ming and
Conde, Marcos",
editor = "Feng, Yansong and
Lefever, Els",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-demo.6/",
doi = "10.18653/v1/2023.emnlp-demo.6",
pages = "82--89",
abstract = "Large Language Models (LLMs) represent a revolution in AI. However, they also pose many significant risks, such as the presence of biased, private, copyrighted or harmful text. For this reason we need open, transparent and safe solutions. We introduce a complete open-source ecosystem for developing and testing LLMs. The goal of this project is to boost open alternatives to closed-source approaches. We release h2oGPT, a family of fine-tuned LLMs from 7 to 70 Billion parameters. We also introduce H2O LLM Studio, a framework and no-code GUI designed for efficient fine-tuning, evaluation, and deployment of LLMs using the most recent state-of-the-art techniques. Our code and models are licensed under fully permissive Apache 2.0 licenses. We believe open-source language models help to boost AI development and make it more accessible and trustworthy. Our demo is available at: https://gpt.h2o.ai/"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="candel-etal-2023-h2o">
<titleInfo>
<title>H2O Open Ecosystem for State-of-the-art Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arno</namePart>
<namePart type="family">Candel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">McKinney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Singer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascal</namePart>
<namePart type="family">Pfeiffer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Jeblick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chun</namePart>
<namePart type="given">Ming</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Conde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yansong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) represent a revolution in AI. However, they also pose many significant risks, such as the presence of biased, private, copyrighted or harmful text. For this reason we need open, transparent and safe solutions. We introduce a complete open-source ecosystem for developing and testing LLMs. The goal of this project is to boost open alternatives to closed-source approaches. We release h2oGPT, a family of fine-tuned LLMs from 7 to 70 Billion parameters. We also introduce H2O LLM Studio, a framework and no-code GUI designed for efficient fine-tuning, evaluation, and deployment of LLMs using the most recent state-of-the-art techniques. Our code and models are licensed under fully permissive Apache 2.0 licenses. We believe open-source language models help to boost AI development and make it more accessible and trustworthy. Our demo is available at: https://gpt.h2o.ai/</abstract>
<identifier type="citekey">candel-etal-2023-h2o</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-demo.6</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-demo.6/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>82</start>
<end>89</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T H2O Open Ecosystem for State-of-the-art Large Language Models
%A Candel, Arno
%A McKinney, Jon
%A Singer, Philipp
%A Pfeiffer, Pascal
%A Jeblick, Maximilian
%A Lee, Chun Ming
%A Conde, Marcos
%Y Feng, Yansong
%Y Lefever, Els
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F candel-etal-2023-h2o
%X Large Language Models (LLMs) represent a revolution in AI. However, they also pose many significant risks, such as the presence of biased, private, copyrighted or harmful text. For this reason we need open, transparent and safe solutions. We introduce a complete open-source ecosystem for developing and testing LLMs. The goal of this project is to boost open alternatives to closed-source approaches. We release h2oGPT, a family of fine-tuned LLMs from 7 to 70 Billion parameters. We also introduce H2O LLM Studio, a framework and no-code GUI designed for efficient fine-tuning, evaluation, and deployment of LLMs using the most recent state-of-the-art techniques. Our code and models are licensed under fully permissive Apache 2.0 licenses. We believe open-source language models help to boost AI development and make it more accessible and trustworthy. Our demo is available at: https://gpt.h2o.ai/
%R 10.18653/v1/2023.emnlp-demo.6
%U https://aclanthology.org/2023.emnlp-demo.6/
%U https://doi.org/10.18653/v1/2023.emnlp-demo.6
%P 82-89
Markdown (Informal)
[H2O Open Ecosystem for State-of-the-art Large Language Models](https://aclanthology.org/2023.emnlp-demo.6/) (Candel et al., EMNLP 2023)
ACL
- Arno Candel, Jon McKinney, Philipp Singer, Pascal Pfeiffer, Maximilian Jeblick, Chun Ming Lee, and Marcos Conde. 2023. H2O Open Ecosystem for State-of-the-art Large Language Models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 82–89, Singapore. Association for Computational Linguistics.