Update README.md

README.md

@@ -1,3 +1,26 @@
 ---
 license: mit
 ---
+
+**INFERENTIA ONLY**
+
+```py
+
+from transformers import AutoTokenizer
+from optimum.neuron import NeuronBertForTokenClassification
+
+input_shapes = {"batch_size": 1, "sequence_length": 128}
+compiler_args = {"auto_cast": "matmul", "auto_cast_type": "bf16"}
+neuron_model = NeuronBertForTokenClassification.from_pretrained(
+    "dslim/bert-base-NER",
+    export=True,
+    **input_shapes,
+    **compiler_args,
+)
+# Save locally
+neuron_model.save_pretrained("bert_base_ner_neuronx")
+neuron_model.push_to_hub(
+    "bert_base_ner_neuronx",
+    repository_id="optimum/bert-base-NER-neuronx",  # Replace with your HF Hub repo id
+)
+```