Spaces:
Configuration error
Configuration error
Download src/processer/tokenizer.py from TencentARC/SEED-Story: direct link, hf CLI and curl.
- Browser
- Download file 348 Bytes
-
https://huggingface.co/spaces/TencentARC/SEED-Story/resolve/main/src/processer/tokenizer.py
- Command line
-
hf download hf://spaces/TencentARC/SEED-Story/src/processer/tokenizer.py
-
curl -L -o tokenizer.py https://huggingface.co/spaces/TencentARC/SEED-Story/resolve/main/src/processer/tokenizer.py
348 Bytes
| from transformers import BertTokenizer | |
| def bert_tokenizer(pretrained_model_name_or_path): | |
| tokenizer = BertTokenizer.from_pretrained(pretrained_model_name_or_path=pretrained_model_name_or_path, | |
| truncation_side='right') | |
| tokenizer.add_special_tokens({"bos_token": "[DEC]"}) | |
| return tokenizer | |