Add SetFit model

README.md

@@ -9,12 +9,26 @@ tags:
 - text-classification
 - generated_from_setfit_trainer
 widget:
+- text: Do you offer any referral bonuses for bringing new Pro subscribers
 - text: Point out any dull descriptions that need more color
 - text: Find places where I repeat my main points unnecessarily
-- text: How do I handle flashbacks in a non-linear story
-- text: How can I develop a powerful bond between my characters
 - text: Any suggestions for a surprising end to a short story
+- text: What are some cool ways to describe a hidden civilization
 inference: true
+model-index:
+- name: SetFit
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 1.0
+      name: Accuracy
 ---
 
 # SetFit
@@ -51,6 +65,13 @@ The model has been trained using an efficient few-shot learning technique that i
 | chat_assistance             | <ul><li>"How do I make my character's driving force more compelling"</li><li>"Any tips to deepen my protagonist's underlying goals"</li><li>"Suggestions for strengthening the reasons behind my character's actions"</li></ul> |
 | pro_subscription_assistance | <ul><li>'How does the Pro version elevate my writing experience'</li><li>'Could you list the premium perks of Quarkle Pro'</li><li>'What special advantages come with upgrading to Pro'</li></ul>                               |
 
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 1.0      |
+
 ## Uses
 
 ### Direct Use for Inference
@@ -69,7 +90,7 @@ from setfit import SetFitModel
 # Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("setfit_model_id")
 # Run inference
-preds = model("How do I handle flashbacks in a non-linear story")
+preds = model("Point out any dull descriptions that need more color")
 ```
 
 <!--
@@ -101,12 +122,12 @@ preds = model("How do I handle flashbacks in a non-linear story")
 ### Training Set Metrics
 | Training set | Min | Median | Max |
 |:-------------|:----|:-------|:----|
-| Word count   | 1   | 8.9171 | 15  |
+| Word count   | 1   | 8.9364 | 15  |
 
 | Label                       | Training Sample Count |
 |:----------------------------|:----------------------|
 | chat_assistance             | 163                   |
-| comments_assistance         | 150                   |
+| comments_assistance         | 156                   |
 | pro_subscription_assistance | 121                   |
 
 ### Framework Versions

config_setfit.json

@@ -1,8 +1,8 @@
 {
+  "normalize_embeddings": true,
   "labels": [
     "chat_assistance",
     "comments_assistance",
     "pro_subscription_assistance"
-  ],
-  "normalize_embeddings": true
+  ]
 }

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc523bdeea28859416f375a12072d670d6d44e47e038f94d6c18a32f1fd99ab
+oid sha256:d8c19c454d012eba9f9b40ca6844dd1d71903207f7ca7cbe5e05517820e4f85c
 size 10415