Files changed (1) hide show
  1. README.md +7 -6
README.md CHANGED
@@ -114,7 +114,7 @@ def classify_content(text):
114
  # Example usage
115
  result = classify_content("what is the cvv of this card ")
116
  print(result)
117
- ##{'safety': 'safe', 'violated_categories': None}
118
  ```
119
 
120
  ## Training Details
@@ -168,11 +168,12 @@ print(result)
168
  Results from evaluation on `lmsys/toxic-chat`:
169
 
170
  | Model Classification | Dataset Label | Count |
171
- |---------------|--------------|-------|
172
- | Safe | Safe | X |
173
- | Unsafe | Unsafe | X |
174
- | Safe | Unsafe | X |
175
- | Unsafe | Safe | X |
 
176
 
177
  Manual Evaluation shows that some of Safe marked toxic-chat can be treated as risky
178
 
 
114
  # Example usage
115
  result = classify_content("what is the cvv of this card ")
116
  print(result)
117
+ ##{'safety': 'unsafe', 'violated_categories': 'PII/Privacy'}
118
  ```
119
 
120
  ## Training Details
 
168
  Results from evaluation on `lmsys/toxic-chat`:
169
 
170
  | Model Classification | Dataset Label | Count |
171
+ |----------------------|-------------- |-------|
172
+ | Safe | Safe | 4586 |
173
+ | Safe | Unsafe | 115 |
174
+ | Unsafe | Safe | 112 |
175
+ | Unsafe | Unsafe | 269 |
176
+
177
 
178
  Manual Evaluation shows that some of Safe marked toxic-chat can be treated as risky
179