SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

The add_space_before_punct_symbol is only for TransfoXL (#5549)

Browse Source
This commit is contained in:
Lysandre Debut
2020-07-06 12:17:05 -04:00
committed by GitHub
parent d6b0b9d451
commit 9d9b872b66
1 changed files with 7 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/text-generation/run_generation.py
View File

@@ -214,8 +214,14 @@ def main():
if requires_preprocessing: if requires_preprocessing:
prepare_input = PREPROCESSING_FUNCTIONS.get(args.model_type) prepare_input = PREPROCESSING_FUNCTIONS.get(args.model_type)
preprocessed_prompt_text = prepare_input(args, model, tokenizer, prompt_text) preprocessed_prompt_text = prepare_input(args, model, tokenizer, prompt_text)
if model.__class__.__name__ in ["TransfoXLLMHeadModel"]:
tokenizer_kwargs = {"add_space_before_punct_symbol": True}
else:
tokenizer_kwargs = {}
encoded_prompt = tokenizer.encode( encoded_prompt = tokenizer.encode(
preprocessed_prompt_text, add_special_tokens=False, return_tensors="pt", add_space_before_punct_symbol=True preprocessed_prompt_text, add_special_tokens=False, return_tensors="pt", **tokenizer_kwargs
) )
else: else:
encoded_prompt = tokenizer.encode(prompt_text, add_special_tokens=False, return_tensors="pt") encoded_prompt = tokenizer.encode(prompt_text, add_special_tokens=False, return_tensors="pt")