Text Classification
Transformers
Safetensors
English
distilbert
moderation
filtering
offensive
clean
Eval Results (legacy)
Eval Results
text-embeddings-inference
Instructions to use aksern/ftan-2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aksern/ftan-2.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="aksern/ftan-2.5")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("aksern/ftan-2.5") model = AutoModelForSequenceClassification.from_pretrained("aksern/ftan-2.5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,109 @@ tags:
|
|
| 13 |
- clean
|
| 14 |
datasets:
|
| 15 |
- akaruineko/fantastic-offensive
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# ftan-2.5
|
|
|
|
| 13 |
- clean
|
| 14 |
datasets:
|
| 15 |
- akaruineko/fantastic-offensive
|
| 16 |
+
model-index:
|
| 17 |
+
- name: akaruineko/ftan-2.5
|
| 18 |
+
results:
|
| 19 |
+
- task:
|
| 20 |
+
type: text-classification
|
| 21 |
+
id: overall
|
| 22 |
+
dataset:
|
| 23 |
+
type: akaruineko/ftanch
|
| 24 |
+
name: FTANch
|
| 25 |
+
split: test
|
| 26 |
+
metrics:
|
| 27 |
+
- type: acc
|
| 28 |
+
value: 0.8366
|
| 29 |
+
name: Accuracy
|
| 30 |
+
- type: p
|
| 31 |
+
value: 0.7999
|
| 32 |
+
name: Precision
|
| 33 |
+
- type: r
|
| 34 |
+
value: 0.9616
|
| 35 |
+
name: Recall
|
| 36 |
+
- type: f1
|
| 37 |
+
value: 0.8733
|
| 38 |
+
name: F1-Score
|
| 39 |
+
- task:
|
| 40 |
+
type: text-classification
|
| 41 |
+
id: test
|
| 42 |
+
dataset:
|
| 43 |
+
type: akaruineko/ftanch
|
| 44 |
+
name: FTANch
|
| 45 |
+
split: test
|
| 46 |
+
metrics:
|
| 47 |
+
- type: acc
|
| 48 |
+
value: 0.8007
|
| 49 |
+
name: Accuracy
|
| 50 |
+
- type: p
|
| 51 |
+
value: 0.7315
|
| 52 |
+
name: Precision
|
| 53 |
+
- type: r
|
| 54 |
+
value: 0.9499
|
| 55 |
+
name: Recall
|
| 56 |
+
- type: f1
|
| 57 |
+
value: 0.8266
|
| 58 |
+
name: F1-Score
|
| 59 |
+
- task:
|
| 60 |
+
type: text-classification
|
| 61 |
+
id: test_obfuscated
|
| 62 |
+
dataset:
|
| 63 |
+
type: akaruineko/ftanch
|
| 64 |
+
name: FTANch
|
| 65 |
+
split: test
|
| 66 |
+
metrics:
|
| 67 |
+
- type: acc
|
| 68 |
+
value: 0.9134
|
| 69 |
+
name: Accuracy
|
| 70 |
+
- type: p
|
| 71 |
+
value: 0.9152
|
| 72 |
+
name: Precision
|
| 73 |
+
- type: r
|
| 74 |
+
value: 0.9778
|
| 75 |
+
name: Recall
|
| 76 |
+
- type: f1
|
| 77 |
+
value: 0.9455
|
| 78 |
+
name: F1-Score
|
| 79 |
+
- task:
|
| 80 |
+
type: text-classification
|
| 81 |
+
id: plain
|
| 82 |
+
dataset:
|
| 83 |
+
type: akaruineko/ftanch
|
| 84 |
+
name: FTANch
|
| 85 |
+
split: test
|
| 86 |
+
metrics:
|
| 87 |
+
- type: acc
|
| 88 |
+
value: 0.7012
|
| 89 |
+
name: Accuracy
|
| 90 |
+
- type: p
|
| 91 |
+
value: 0.4647
|
| 92 |
+
name: Precision
|
| 93 |
+
- type: r
|
| 94 |
+
value: 0.8784
|
| 95 |
+
name: Recall
|
| 96 |
+
- type: f1
|
| 97 |
+
value: 0.6078
|
| 98 |
+
name: F1-Score
|
| 99 |
+
- task:
|
| 100 |
+
type: text-classification
|
| 101 |
+
id: mutated
|
| 102 |
+
dataset:
|
| 103 |
+
type: akaruineko/ftanch
|
| 104 |
+
name: FTANch
|
| 105 |
+
split: test
|
| 106 |
+
metrics:
|
| 107 |
+
- type: acc
|
| 108 |
+
value: 0.9134
|
| 109 |
+
name: Accuracy
|
| 110 |
+
- type: p
|
| 111 |
+
value: 0.9152
|
| 112 |
+
name: Precision
|
| 113 |
+
- type: r
|
| 114 |
+
value: 0.9778
|
| 115 |
+
name: Recall
|
| 116 |
+
- type: f1
|
| 117 |
+
value: 0.9455
|
| 118 |
+
name: F1-Score
|
| 119 |
---
|
| 120 |
|
| 121 |
# ftan-2.5
|