Update README.md

README.md

@@ -21,14 +21,14 @@ def mean_pooling(model_output, attention_mask):
     token_embeddings = model_output[0] #First element of model_output contains all token embeddings
     input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
     sum_embeddings = torch.sum(token_embeddings * input_mask_expanded, 1)
-    sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+    sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-10)
     return sum_embeddings / sum_mask
 #Sentences we want sentence embeddings for
 sentences = ['Привет! Как твои дела?',
              'А правда, что 42 твое любимое число?']
 #Load AutoModel from huggingface model repository
-tokenizer = AutoTokenizer.from_pretrained("Andrilko/ru_s_electra_small")
-model = AutoModel.from_pretrained("Andrilko/ru_s_electra_small")
+tokenizer = AutoTokenizer.from_pretrained("sberbank-ai/ru_s_electra_small")
+model = AutoModel.from_pretrained("sberbank-ai/ru_s_electra_small")
 #Tokenize sentences
 encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=24, return_tensors='pt')
 #Compute token embeddings
@@ -36,4 +36,5 @@ with torch.no_grad():
     model_output = model(**encoded_input)
 #Perform pooling. In this case, mean pooling
 sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
-```
+```
+created by Aleksandr Abramov (Andrilko)