Update README.md

README.md

@@ -1,3 +1,48 @@
 ---
+language:
+- zh
 license: mit
 ---
+
+# SimCSE(sup)
+
+## Uses
+You can use our model for encoding sentences into embeddings
+```python
+import torch
+from transformers import BertTokenizer
+from transformers import BertModel
+from sklearn.metrics.pairwise import cosine_similarity
+
+# model
+simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
+tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
+MODEL = BertModel.from_pretrained(simcse_sup_path)
+
+def get_vector_simcse(sentence):
+    """
+    预测simcse的语义向量。
+    """
+    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
+    output = MODEL(input_ids)
+    return output.last_hidden_state[:, 0].squeeze(0)
+
+embeddings = get_vector_simcse("武汉是一个美丽的城市。")
+print(embeddings.shape)
+#torch.Size([768])
+```
+
+You can also compute the cosine similarities between two sentences
+```python
+def get_similarity_two(sentence1, sentence2):
+    vec1 = get_vector_simcse(sentence1).tolist()
+    vec2 = get_vector_simcse(sentence2).tolist()
+    similarity_list = cosine_similarity([vec1], [vec2]).tolist()[0][0]
+    return similarity_list
+
+sentence1 = '你好吗'
+sentence2 = '你还好吗'
+result = get_similarity_two(sentence1,sentence2)
+print(result)
+#0.848331
+```