Update README.md

README.md

@@ -67,4 +67,43 @@ Additional hard/soft negatives may include unrelated meanings.
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/644addfe9279988e0cbc296b/TWHyVDItYwNbFEyI0i--n.png)
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/644addfe9279988e0cbc296b/o-CFHkDYw62Lyh1MKvG4M.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/644addfe9279988e0cbc296b/o-CFHkDYw62Lyh1MKvG4M.png)
+
+
+## How to use
+
+Sentence-Transformers:
+``` python
+# Python
+from sentence_transformers import SentenceTransformer, util
+
+model = SentenceTransformer("radlab/semantic-euro-bert-encoder-v1", trust_remote_code=True)
+
+texts = ["zamek", "drzwi", "wiadro", "horyzont", "ocean"]
+emb = model.encode(texts, convert_to_tensor=True, normalize_embeddings=True)
+scores = util.cos_sim(emb, emb)
+print(scores)  # higher = more semantically similar
+```
+
+Transformers (feature extraction):
+``` python
+# Python
+from transformers import AutoModel, AutoTokenizer
+import torch
+import torch.nn.functional as F
+
+name = "radlab/semantic-euro-bert-encoder-v1"
+tok = AutoTokenizer.from_pretrained(name)
+mdl = AutoModel.from_pretrained(name, trust_remote_code=True)
+
+texts = ["student", "żak"]
+tokens = tok(texts, padding=True, truncation=True, return_tensors="pt")
+with torch.no_grad():
+    out = mdl(**tokens)
+    # simple mean pooling over tokens; use model-specific pooling if provided
+    emb = out.last_hidden_state.mean(dim=1)
+    emb = F.normalize(emb, p=2, dim=1)
+
+sim = emb @ emb.T
+print(sim)
+```