Create app.py

app.py

@@ -0,0 +1,26 @@
+!pip install transformers
+from transformers import AutoTokenizer, AutoModel
+from torch.nn import functional as F
+tokenizer = AutoTokenizer.from_pretrained('deepset/sentence_bert')
+model = AutoModel.from_pretrained('deepset/sentence_bert')
+
+sentence = 'Who are you voting for in 2020?'
+labels = ['business', 'art & culture', 'politics']
+
+# run inputs through model and mean-pool over the sequence
+# dimension to get sequence-level representations
+inputs = tokenizer.batch_encode_plus([sentence] + labels,
+                                     return_tensors='pt',
+                                     pad_to_max_length=True)
+input_ids = inputs['input_ids']
+attention_mask = inputs['attention_mask']
+output = model(input_ids, attention_mask=attention_mask)[0]
+sentence_rep = output[:1].mean(dim=1)
+label_reps = output[1:].mean(dim=1)
+
+# now find the labels with the highest cosine similarities to
+# the sentence
+similarities = F.cosine_similarity(sentence_rep, label_reps)
+closest = similarities.argsort(descending=True)
+for ind in closest:
+    print(f'label: {labels[ind]} \t similarity: {similarities[ind]}')