Modify space token to <_>

Change space token from <th_roberta_space_token> to <_>

Add pretrained_model_name_or_path

Merge branch 'main' of https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased into main

initial commit

Add pretrained wangchanberta-base-att-spm-uncased model

Add vocab file and tokenizer_config.json

Init project

initial commit