TaCoGPT

Description

TaCoGPT is a large language model employed for the taxonomic classification of microbial sequences.

Write interface function to do training and inference.

Install the requirements for the requirements.txt file.

Pre-train model

python script_pretrain_TaCoGPT_ddp.py

Fine-tune model with all data:

python script_train_TaCoGPT_ddp_All.py

Fine-tune model with removed clades data.

python script_train_TaCoGPT_ddp_Rm.py

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
.vscode		.vscode
InfoFiles_AllClade		InfoFiles_AllClade
InfoFiles_RmClade		InfoFiles_RmClade
TaCoGPT		TaCoGPT
README.md		README.md
requirements.txt		requirements.txt
script_pretrain_TaCoGPT_ddp.py		script_pretrain_TaCoGPT_ddp.py
script_train_TaCoGPT_ddp_All.py		script_train_TaCoGPT_ddp_All.py
script_train_TaCoGPT_ddp_Rm.py		script_train_TaCoGPT_ddp_Rm.py