Extra Large Language Models Benchmarking for Medicinal Chemistry

Fuente: Zenodo
Enregistré dans:
Détails bibliographiques
Auteur principal: Kawchak, Kevin
Format: Recurso digital
Langue:anglais
Publié: Zenodo 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866901396126695424
author Kawchak, Kevin
author_facet Kawchak, Kevin
contents <p>Purpose: Determine which unmodified Extra Large Language Model has the greatest speed and generation quality answering medicinal chemistry prompts. Plan: Use OpenAI API for GPT 4o, and NVIDIA NIM API for Nemotron 4, Mixtral, and Arctic. To judge generations, use ChatGPT 4o and Llama 3 70B Groq. Experimental: In a Colab notebook for either OpenAI API or NIM API, answer 10 medicinal chemistry prompts. Manually process all generations, and further analyze the first three prompts three times each with both judges.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_14968018
institution Zenodo
language eng
publishDate 2024
publisher Zenodo
record_format zenodo
spellingShingle Extra Large Language Models Benchmarking for Medicinal Chemistry
Kawchak, Kevin
OpenAI
NVIDIA
Mistral
Drug Synthesis
LLM
Prompt Engineering
<p>Purpose: Determine which unmodified Extra Large Language Model has the greatest speed and generation quality answering medicinal chemistry prompts. Plan: Use OpenAI API for GPT 4o, and NVIDIA NIM API for Nemotron 4, Mixtral, and Arctic. To judge generations, use ChatGPT 4o and Llama 3 70B Groq. Experimental: In a Colab notebook for either OpenAI API or NIM API, answer 10 medicinal chemistry prompts. Manually process all generations, and further analyze the first three prompts three times each with both judges.</p>
title Extra Large Language Models Benchmarking for Medicinal Chemistry
topic OpenAI
NVIDIA
Mistral
Drug Synthesis
LLM
Prompt Engineering
url https://doi.org/10.5281/zenodo.14968018