Update README.md

README.md

@@ -12,9 +12,39 @@ This model identifies common events and patterns within the conversation flow. S
 
 This model should be used *only* for user dialogs.
 
-# Usage
+
+# Optimum
 
 ## Installation
+
+Install from source: 
+```bash
+python -m pip install optimum[onnxruntime]@git+https://github.com/huggingface/optimum.git
+```
+
+
+## Run the Model
+```py
+from optimum.onnxruntime import ORTModelForSequenceClassification
+from transformers import AutoTokenizer, pipeline
+
+model = ORTModelForSequenceClassification.from_pretrained('Ngit/MiniLMv2-userflow-v2-onnx', provider="CPUExecutionProvider")
+tokenizer = AutoTokenizer.from_pretrained('Ngit/MiniLMv2-userflow-v2-onnx', use_fast=True, model_max_length=256, truncation=True, padding='max_length')
+
+pipe = pipeline(task='text-classification', model=model, tokenizer=tokenizer, )
+texts = ["that's wrong", "can you please answer me?"]
+pipe(texts)
+# [{'label': 'model_wrong_or_try_again', 'score': 0.9737648367881775},
+# {'label': 'user_wants_agent_to_answer', 'score': 0.9105103015899658}]
+```
+
+
+# ONNX Runtime only
+
+A lighter solution for deployment
+
+## Installation 
+
 ```bash
 pip install tokenizers
 pip install onnxruntime
@@ -43,7 +73,9 @@ tokenizer.enable_padding(
 tokenizer.enable_truncation(max_length=256)
 batch_size = 16
 
-texts = ["I am angry", "I feel in love"]
+texts = ["that's wrong", "can you please answer me?"]
+
+
 outputs = []
 model = InferenceSession("MiniLMv2-userflow-v2-onnx/model_optimized_quantized.onnx", providers=['CPUExecutionProvider'])
 
@@ -100,8 +132,8 @@ for result in results:
     res.append(max_score)
 
 res
-#[('model_wrong_or_try_again', 0.9982967972755432),
-# ('user_wants_agent_to_answer', 0.996489942073822)]
+#[('model_wrong_or_try_again', 0.9737648367881775),
+# ('user_wants_agent_to_answer', 0.9105103015899658)]
 ```
 
 # Categories Explanation