You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
zhanghangit bf716fb7c0 add nvidia megatron code 3 years ago
..
scripts add nvidia megatron code 3 years ago
__init__.py add nvidia megatron code 3 years ago
configure_data.py add nvidia megatron code 3 years ago
corpora.py add nvidia megatron code 3 years ago
datasets.py add nvidia megatron code 3 years ago
file_utils.py add nvidia megatron code 3 years ago
lazy_loader.py add nvidia megatron code 3 years ago
samplers.py add nvidia megatron code 3 years ago
tf_dl.py add nvidia megatron code 3 years ago
tokenization.py add nvidia megatron code 3 years ago
tokenization_gpt2.py add nvidia megatron code 3 years ago
wordpiece.py add nvidia megatron code 3 years ago

使用100G中文高质量语料,128张V100,训练的中文Megatron模型,参数量2.6B

Python C++ Shell Cuda TeX other

Contributors (2)