update readme

README.md

@@ -34,11 +34,13 @@ widget:
       translate to zh: Цель разработки — предоставить пользователям личного синхронного переводчика.
 ---
 
-# T5 English, Russian and Chinese multilingual machine translation
+# T5 English, Russian and Chinese sentence similarity model
 
 This is a [sentence-transformers](https://www.sbert.net/) model: It maps sentences & paragraphs to a 768 dimensional dense vector space. The model works well for sentence similarity tasks, but doesn't perform that well for semantic search tasks.
 
-The model uses only the encoder from a T5-base model.
+The model can be used to search for parallel texts in Russian, English and Chinese.
+
+To determine the similarity of sentences in the model, only the encoder from the T5-based model is used.
 
 
 ## Usage (Sentence-Transformers)
@@ -49,6 +51,8 @@ Using this model becomes easy when you have [sentence-transformers](https://www.
 pip install -U sentence-transformers
 ```
 
+
+
 Then you can use the model like this:
 
 ```python
@@ -87,7 +91,7 @@ from transformers import T5ForConditionalGeneration, T5Tokenizer
 
 device = 'cuda' #or 'cpu' for translate on cpu
 
-model_name = 'utrobinmv/t5_translate_en_ru_zh_large_1024'
+model_name = 'utrobinmv/t5_translate_en_ru_zh_base_200_sent'
 model = T5ForConditionalGeneration.from_pretrained(model_name)
 model.to(device)
 tokenizer = T5Tokenizer.from_pretrained(model_name)
@@ -114,7 +118,7 @@ from transformers import T5ForConditionalGeneration, T5Tokenizer
 
 device = 'cuda' #or 'cpu' for translate on cpu
 
-model_name = 'utrobinmv/t5_translate_en_ru_zh_large_1024'
+model_name = 'utrobinmv/t5_translate_en_ru_zh_base_200_sent'
 model = T5ForConditionalGeneration.from_pretrained(model_name)
 model.to(device)
 tokenizer = T5Tokenizer.from_pretrained(model_name)