Text Classification
Transformers
ONNX
Safetensors
llama
safety
content-moderation
multi-label
multilingual
tiny-language-model
from-scratch
distilled
text-embeddings-inference
Instructions to use KucLab/Censer.8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Censer.8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Censer.8")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Censer.8") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Censer.8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add report multilingual.md
Browse files- reports/multilingual.md +23 -0
reports/multilingual.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Multilingual eval
|
| 2 |
+
|
| 3 |
+
| set | n | unsafe | F1@0.5 | acc@0.5 | best F1 |
|
| 4 |
+
| --- | --- | --- | --- | --- | --- |
|
| 5 |
+
| textdetox_am | 800 | 385 | 0.1016 | 0.5138 | 0.4228571428571429 |
|
| 6 |
+
| textdetox_ar | 800 | 387 | 0.0051 | 0.5150 | 0.0995260663507109 |
|
| 7 |
+
| textdetox_de | 800 | 397 | 0.5583 | 0.5687 | 0.6765249537892791 |
|
| 8 |
+
| textdetox_en | 800 | 391 | 0.8136 | 0.7950 | 0.8368421052631578 |
|
| 9 |
+
| textdetox_es | 800 | 408 | 0.6192 | 0.5787 | 0.672929120409906 |
|
| 10 |
+
| textdetox_fr | 800 | 391 | 0.4839 | 0.6000 | 0.6764976958525346 |
|
| 11 |
+
| textdetox_he | 800 | 332 | 0.0294 | 0.5875 | 0.19948849104859337 |
|
| 12 |
+
| textdetox_hi | 800 | 409 | 0.0000 | 0.4888 | 0.009732360097323601 |
|
| 13 |
+
| textdetox_hin | 800 | 394 | 0.5030 | 0.5800 | 0.6386740331491714 |
|
| 14 |
+
| textdetox_it | 800 | 409 | 0.5685 | 0.5825 | 0.6765922249793217 |
|
| 15 |
+
| textdetox_ja | 800 | 409 | 0.0000 | 0.4888 | 0.0 |
|
| 16 |
+
| textdetox_ru | 800 | 391 | 0.2232 | 0.5475 | 0.6358267716535433 |
|
| 17 |
+
| textdetox_tt | 800 | 403 | 0.4331 | 0.5288 | 0.6391959798994975 |
|
| 18 |
+
| textdetox_uk | 800 | 391 | 0.2470 | 0.5350 | 0.6296992481203008 |
|
| 19 |
+
| textdetox_zh | 800 | 409 | 0.0000 | 0.4863 | 0.2086614173228346 |
|
| 20 |
+
| synth_cs | 300 | 150 | 1.0000 | 1.0000 | — |
|
| 21 |
+
| synth_de | 300 | 150 | 1.0000 | 1.0000 | — |
|
| 22 |
+
| synth_es | 300 | 150 | 1.0000 | 1.0000 | — |
|
| 23 |
+
| synth_fr | 300 | 150 | 1.0000 | 1.0000 | — |
|