Update README.md

README.md

@@ -7,7 +7,7 @@ tags:
 - e-commerce
 pipeline_tag: fill-mask
 widget:
-- text: летнее легкое
+- text: электроника зарядка [MASK] USB
 library_name: transformers
 ---
 
@@ -20,7 +20,7 @@ A model for solving the problem of missing words in search queries. The model us
 # pip install protobuf sentencepiece
 
 from transformers import pipeline
-unmasker = pipeline('fill-mask', model='fkrasnov2/COLD2', device='cuda')
+unmasker = pipeline("fill-mask", model="fkrasnov2/COLD2", device="cuda")
 unmasker("электроника зарядка [MASK] USB")
 
 [{'score': 0.3712620437145233,
@@ -46,7 +46,7 @@ unmasker("электроника зарядка [MASK] USB")
 
 ```
 
-Related prepositions and prompts can be used to improve tokenization.
+Coupled prepositions can be used to improve tokenization.
 
 
 ```python