Update README.md

README.md

@@ -1,3 +1,46 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+base_model:
+- Snowflake/snowflake-arctic-embed-l
+---
+
+***This model is a neuron compiled version of https://huggingface.co/Snowflake/snowflake-arctic-embed-l ***
+
+It was compiled on version 2.20 of the Neuron SDK.  You may need to run the compilation process again.
+
+See https://huggingface.co/docs/optimum-neuron/en/inference_tutorials/sentence_transformers for more details
+
+For information on how to run on SageMaker:  https://huggingface.co/docs/optimum-neuron/en/inference_tutorials/sentence_transformers
+
+To run:
+```
+
+from optimum.neuron import NeuronModelForSentenceTransformers
+from transformers import AutoTokenizer
+model_id = "jburtoft/snowflake-arctic-embed-l"
+
+# Use the line below if you have to compile the model yourself
+#model_id = "snowflake-arctic-embed-l-inf2"
+
+
+model = NeuronModelForSentenceTransformers.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+# Run inference
+prompt = "I like to eat apples"
+encoded_input = tokenizer(prompt, return_tensors='pt')
+outputs = model(**encoded_input)
+
+token_embeddings = outputs.token_embeddings
+sentence_embedding = outputs.sentence_embedding
+
+print(f"token embeddings: {token_embeddings.shape}") # torch.Size([1, 7, 384])
+print(f"sentence_embedding: {sentence_embedding.shape}") # torch.Size([1, 384])
+
+```
+
+To compile :
+```
+optimum-cli export neuron -m Snowflake/snowflake-arctic-embed-l --sequence_length 512 --batch_size 1 --task feature-extraction snowflake-arctic-embed-l-inf2
+```
+