update readme

README.md

@@ -7,9 +7,9 @@ datasets:
 - uspto
 ---
 
-# Adapter `doncamilom/OChemSegm-flan-T5-large` for None
+# Adapter `doncamilom/OChemSegm-flan-T5-large` for google/flan-t5-large
 
-An [adapter](https://adapterhub.ml) for the `None` model that was trained on the [chemistry](https://adapterhub.ml/explore/chemistry/) dataset.
+An [adapter](https://adapterhub.ml) for the `google/flan-t5-large` model that was trained on the [USPTO-segment](www.tobedone.undone) dataset.
 
 This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
 
@@ -25,10 +25,19 @@ _Note: adapter-transformers is a fork of transformers that acts as a drop-in rep
 Now, the adapter can be loaded and activated like this:
 
 ```python
-from transformers import AutoAdapterModel
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
-model = AutoAdapterModel.from_pretrained("None")
-adapter_name = model.load_adapter("doncamilom/OChemSegm-flan-T5-large", source="hf", set_active=True)
+adapter = 'doncamilom/OChemSegm-flan-T5-large'
+
+model = AutoModelForSeq2SeqLM.from_pretrained(
+    'google/flan-t5-large',
+)
+
+# Load adapter
+adapter_name = self.model.load_adapter(adapter, source='hf', set_active=True)
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(adapter)
 ```
 
 ## Architecture & Training
@@ -41,4 +50,4 @@ adapter_name = model.load_adapter("doncamilom/OChemSegm-flan-T5-large", source="
 
 ## Citation
 
-<!-- Add some description here -->
+<!-- Add some description here -->