C

Chemgpt 1.2B

Developed by ncfrey
ChemGPT is a generative molecular modeling tool based on the GPT-Neo model, specializing in molecular generation and research in the field of chemistry.
Downloads 409
Release Time : 5/11/2022

Model Overview

ChemGPT is a transformers model specifically designed for generative molecular modeling. The model was pretrained on the PubChem10M dataset, primarily to study the impact of pretraining and fine-tuning on downstream datasets.

Model Features

Chemistry-Specific Pretraining
Pretrained specifically on the PubChem10M dataset for chemical molecules, optimizing molecular generation capabilities.
SELFIES Format Conversion
Uses the SELFIES library to convert SMILES strings into the more stable SELFIES format for training.
Research-Oriented Design
Primarily designed to study the impact of pretraining and fine-tuning on downstream chemical datasets.

Model Capabilities

Molecular Generation
Chemical Structure Modeling
Molecular Property Prediction

Use Cases

Chemical Research
New Molecule Design
Generate potential novel molecular structures for drug discovery
Chemical Model Research
Study the impact of pretraining on downstream chemical tasks
Education
Chemistry Teaching Aid
Generate example molecules for chemistry teaching demonstrations
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase