Update README.md

README.md

@@ -15,4 +15,31 @@ tags:
 
 The base version of [roberta-base](https://huggingface.co/roberta-base) finetunned on an artificially annotated subset of C4. This model provides domain-independent embedding for Entity Recognition Task. Embeddings can be used out of the box or fine-tuned on specific datasets. 
 
-## Usage
+## Usage
+
+```python
+import torch
+import transformers
+
+
+model = transformers.AutoModel.from_pretrained(
+    'numind/entity-recognition-general-sota-v1',
+    output_hidden_states=True
+)
+tokenizer = transformers.AutoTokenizer.from_pretrained(
+    'numind/entity-recognition-general-sota-v1'
+)
+
+text = "NuMind is an AI company based in Paris and USA."
+encoded_input = tokenizer(text, return_tensors='pt')
+output = model(**encoded_input)
+
+# for better quality
+emb = torch.cat(
+    (output.hidden_states[-1], output.hidden_states[-7]),
+    dim=2
+)
+
+# for better speed
+# emb = output.hidden_states[-1]
+```