hku_diffusion_dllm / reference /code /flm /configs /data /fineweb-edu.yaml
Ouzhang's picture
Add files using upload-large-folder tool
31dc8dc verified
Raw
History Blame Contribute Delete
192 Bytes
train: HuggingFaceFW/fineweb-edu
valid: openwebtext-valid #wikitext103
tokenizer_name_or_path: gpt2
cache_dir: ./cache
wrap: True
streaming: True
insert_train_eos: True
insert_valid_eos: True