Update README.md

README.md

@@ -15,6 +15,20 @@ The encoder model extracted from [flan-ul2](https://huggingface.co/google/flan-u
 
 ## basic usage
 
+```python
+from transformers import AutoTokenizer, AutoModelForTextEncoding
+
+tokenizer = AutoTokenizer.from_pretrained("pszemraj/flan-ul2-text-encoder")
+model = AutoModelForTextEncoding.from_pretrained("pszemraj/flan-ul2-text-encoder")
+
+inputs = tokenizer("Hello, my dog loves memes", return_tensors="pt")
+outputs = model(**inputs)
+
+last_hidden_states = outputs.last_hidden_state
+```
+
+## usage: semantic similarity 
+
 > note: this is 'one way' to use the encoder, not 'the only way'. suggestions and ideas welcome.
 
 Below is an example and a set of functions to compute the cosine similarity between the embeddings of different texts with this model