Update README.md

README.md

@@ -27,10 +27,13 @@ model-index:
 ---
 
 
-# Information Content Classification using SetFit with Base sentence-transformers/paraphrase-mpnet-base-v2
+# Onyx Information Content Classification using SetFit with Base sentence-transformers/paraphrase-mpnet-base-v2
 
-This is a model based on the [SetFit](https://github.com/huggingface/setfit) approach. It is used to identify whether a short text segmant
-contains information that could be useful by itself to answer a RAG-type question. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A trained [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
+The model is for use by the [Onyx Enterprise Search](https://github.com/onyx-dot-app/onyx) system to identify whether a short 
+text segment contains information that could be useful by itself to answer a RAG-type question.
+
+It is based on the [SetFit](https://github.com/huggingface/setfit) approach, using [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. 
+A trained [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
 
 The model has been trained using an efficient few-shot learning technique that involves:
 
@@ -54,18 +57,14 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
 - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
 
-### Model Labels
-| Label | Examples                                                                                      |
-|:------|:----------------------------------------------------------------------------------------------|
-| 1     | <ul><li>'Paris is in France'</li><li>'Time != Money'</li><li>'TBA - to be announced'</li></ul> |
-| 0     | <ul><li>'Food delivery'</li><li>'She was not aware of the birds'</li><li>'The Eiffel Tower'</li></ul>             |
-
 
 ## Uses
 
-### Direct Use for Inference
+### Use for Inference
+
+The model is for use by the Onyx Enterprise Search system.
 
-First install the SetFit library:
+To test it locally, first install the SetFit library:
 
 ```bash
 pip install setfit
@@ -77,9 +76,11 @@ Then you can load this model and run inference.
 from setfit import SetFitModel
 
 # Download from the 🤗 Hub
-model = SetFitModel.from_pretrained(<setfit_model_id>)
+model = SetFitModel.from_pretrained("onyx-dot-app/information-content-model")
 # Run inference
 preds = model("Paris is in France")
+or:
+pred_probability = model.predict_proba("Paris is in France")
 ```
 
 ### Framework Versions