Create f.py

f.py

@@ -0,0 +1,17 @@
+# pip install transformers sentencepiece
+import torch
+from transformers import AutoTokenizer, AutoModel
+tokenizer = AutoTokenizer.from_pretrained("cointegrated/rubert-tiny2")
+model = AutoModel.from_pretrained("cointegrated/rubert-tiny2")
+# model.cuda()  # uncomment it if you have a GPU
+
+def embed_bert_cls(text, model, tokenizer):
+    t = tokenizer(text, padding=True, truncation=True, return_tensors='pt')
+    with torch.no_grad():
+        model_output = model(**{k: v.to(model.device) for k, v in t.items()})
+    embeddings = model_output.last_hidden_state[:, 0, :]
+    embeddings = torch.nn.functional.normalize(embeddings)
+    return embeddings[0].cpu().numpy()
+
+print(embed_bert_cls('привет мир', model, tokenizer).shape)
+# (312,)