Downloads · 30 days
0
ayushnoori/alive
alive is a machine learning model from ayushnoori. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as llama2.
ALIVE is an artificial intelligence-based recommendation system for longevity supplementation and drug repurposing. Based on your unique biological profile, ALIVE will recommend a personalized regimen of supplements a…
Downloads · 30 days
0
Access
Public
Updated Feb 18, 2024
Repo size
17.3 MB
Likes
1
Public
Click a slice to open those files.
.safetensors16.8 MB · 88%
From the Hugging Face model README
ALIVE is an artificial intelligence-based recommendation system for longevity supplementation and drug repurposing. Based on your unique biological profile, ALIVE will recommend a personalized regimen of supplements and drugs to optimize your healthspan. ALIVE places control over your healthspan into your own hands.
The large language model (LLM) that underlies ALIVE was initialized from meta-llama/Llama-2-7b-chat-hf and was fine-tuned using Monster API on the filtered DrugAge database, a database of aging related drugs. We used the following prompt for fine-tuning:
You are an expert drug development scientist and biomedical researcher studying drugs that can promote longevity and extend healthspan. You must answer an important question. Generate a response that answers this question.
###Question: If you administer the compound {compound_name} in a {species} {strain} {gender} model organism at {dosage} dosage, what will the average lifespan change be in years?
###Response: The average lifespan change will be {avg_lifespan_change} years.
ALIVE was built for TreeHacks 2024 at Stanford University. For more details, please see ayushnoori/alive on GitHub.
Training results are available via Weights & Biases at this dashboard.