Readme with Neuron

README.md

@@ -135,6 +135,27 @@ Whitepaper coming soon!
 
 Gradient is accelerating AI transformation across industries. https://gradient.ai/
 
+## Usage with AWS Neuron
+```
+from transformers import AutoTokenizer
+from optimum.neuron import NeuronModelForCausalLM
+
+# Instantiate and convert to Neuron a PyTorch checkpoint
+model = NeuronModelForCausalLM.from_pretrained("gradientai/v-alpha-tross")
+
+tokenizer = AutoTokenizer.from_pretrained("gradientai/v-alpha-tross")
+
+tokens = tokenizer("I really wish ", return_tensors="pt")
+with torch.inference_mode():
+    sample_output = model.generate(
+        **tokens,
+        min_length=16,
+        max_length=32,
+    )
+    outputs = [tokenizer.decode(tok) for tok in sample_output]
+    print(outputs)
+```
+
 ## Contact Us
 
 Drop an email to [contact@gradient.ai](mailto:contact@gradient.ai)