File size: 220 Bytes
93cd35a
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
train: openwebtext-train
valid: openwebtext-valid
modality: text
tokenizer_name_or_path: gpt2
cache_dir: /share/kuleshov/ssahoo/textdiffusion/data
wrap: True
streaming: False
insert_train_eos: True
insert_valid_eos: True