Comparison of Large Language Models for Deployment Requirements

TL;DR

This paper provides a comparative overview of large language models, focusing on features like licensing and hardware needs, to aid researchers and companies in selecting suitable models amidst rapid advancements.

Contribution

It offers a continuously updated GitLab list comparing foundational and domain-specific LLMs based on key deployment features.

Findings

Compiled a comprehensive list of LLMs with licensing and hardware details

Facilitates informed decision-making for LLM deployment

Addresses the challenge of model selection in a rapidly evolving landscape

Abstract

Large Language Models (LLMs), such as Generative Pre-trained Transformers (GPTs) are revolutionizing the generation of human-like text, producing contextually relevant and syntactically correct content. Despite challenges like biases and hallucinations, these Artificial Intelligence (AI) models excel in tasks, such as content creation, translation, and code generation. Fine-tuning and novel architectures, such as Mixture of Experts (MoE), address these issues. Over the past two years, numerous open-source foundational and fine-tuned models have been introduced, complicating the selection of the optimal LLM for researchers and companies regarding licensing and hardware requirements. To navigate the rapidly evolving LLM landscape and facilitate LLM selection, we present a comparative list of foundational and domain-specific models, focusing on features, such as release year, licensing, and hardware requirements. This list is published on GitLab and will be continuously updated.