This commit is contained in:
Sam Shleifer 2020-11-05 11:42:24 -05:00 committed by GitHub
parent 52f44dd6d2
commit 7abc1d96d1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -269,7 +269,7 @@ class Seq2SeqDataCollator:
), f"pad_token_id is not defined for ({self.tokenizer.__class__.__name__}), it must be defined."
self.data_args = data_args
self.tpu_num_cores = tpu_num_cores
self.dataset_kwargs = {"add_prefix_space": isinstance(tokenizer, BartTokenizer)}
self.dataset_kwargs = {"add_prefix_space": True} if isinstance(tokenizer, BartTokenizer) else {}
if data_args.src_lang is not None:
self.dataset_kwargs["src_lang"] = data_args.src_lang
if data_args.tgt_lang is not None: