Text Classification
Transformers
PyTorch
ONNX
Safetensors
English
deberta
Trained with AutoTrain
Inference Endpoints
DarwinAnim8or commited on
Commit
9c944b5
1 Parent(s): 430b7ae

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -4
README.md CHANGED
@@ -88,11 +88,42 @@ Or Python API:
88
  ```python
89
  from transformers import AutoModelForSequenceClassification, AutoTokenizer
90
 
91
- model = AutoModelForSequenceClassification.from_pretrained("KoalaAI/Text-Moderation", use_auth_token=True)
92
-
93
- tokenizer = AutoTokenizer.from_pretrained("KoalaAI/Text-Moderation", use_auth_token=True)
94
 
 
95
  inputs = tokenizer("I love AutoTrain", return_tensors="pt")
96
-
97
  outputs = model(**inputs)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  ```
 
88
  ```python
89
  from transformers import AutoModelForSequenceClassification, AutoTokenizer
90
 
91
+ # Load the model and tokenizer
92
+ model = AutoModelForSequenceClassification.from_pretrained("KoalaAI/Text-Moderation")
93
+ tokenizer = AutoTokenizer.from_pretrained("KoalaAI/Text-Moderation")
94
 
95
+ # Run the model on your input
96
  inputs = tokenizer("I love AutoTrain", return_tensors="pt")
 
97
  outputs = model(**inputs)
98
+
99
+ # Get the predicted logits
100
+ logits = outputs.logits
101
+
102
+ # Apply softmax to get probabilities (scores)
103
+ probabilities = logits.softmax(dim=-1).squeeze()
104
+
105
+ # Retrieve the labels
106
+ id2label = model.config.id2label
107
+ labels = [id2label[idx] for idx in range(len(probabilities))]
108
+
109
+ # Combine labels and probabilities, then sort
110
+ label_prob_pairs = list(zip(labels, probabilities))
111
+ label_prob_pairs.sort(key=lambda item: item[1], reverse=True)
112
+
113
+ # Print the sorted results
114
+ for label, probability in label_prob_pairs:
115
+ print(f"Label: {label} - Probability: {probability:.4f}")
116
+ ```
117
+
118
+ The output of the above Python code will look like this:
119
+ ```
120
+ Label: OK - Probability: 0.9840
121
+ Label: H - Probability: 0.0043
122
+ Label: SH - Probability: 0.0039
123
+ Label: V - Probability: 0.0019
124
+ Label: S - Probability: 0.0018
125
+ Label: HR - Probability: 0.0015
126
+ Label: V2 - Probability: 0.0011
127
+ Label: S3 - Probability: 0.0010
128
+ Label: H2 - Probability: 0.0006
129
  ```