Fix docstring of CLIPTokenizer(Fast) (#20233)

src/transformers/models/clip/tokenization_clip.py

@@ -275,7 +275,7 @@ class CLIPTokenizer(PreTrainedTokenizer):
         unk_token (`str`, *optional*, defaults to `<|endoftext|>`):
             The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
             token instead.
-        bos_token (`str`, *optional*, defaults to `<|endoftext|>`):
+        bos_token (`str`, *optional*, defaults to `<|startoftext|>`):
             The beginning of sequence token.
         eos_token (`str`, *optional*, defaults to `<|endoftext|>`):
             The end of sequence token.

src/transformers/models/clip/tokenization_clip_fast.py

@@ -63,7 +63,7 @@ class CLIPTokenizerFast(PreTrainedTokenizerFast):
         unk_token (`str`, *optional*, defaults to `<|endoftext|>`):
             The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
             token instead.
-        bos_token (`str`, *optional*, defaults to `<|endoftext|>`):
+        bos_token (`str`, *optional*, defaults to `<|startoftext|>`):
             The beginning of sequence token.
         eos_token (`str`, *optional*, defaults to `<|endoftext|>`):
             The end of sequence token.