tangled-llama-t-128k-base-v0.1 / scripts /prepare_pretrain_dataset.py

Commit History

pretrain model
6d9772d

mtasic85 commited on

pretrain dataset
a4a75cd

mtasic85 commited on

compress pretrain dataset
b2e9443

mtasic85 commited on

multilingual dataset
39a4b5b

mtasic85 commited on

initial version
adf4b14

mtasic85 commited on