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/Barist.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Barist.3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Barist.3")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Barist.3") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Barist.3", 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 (textdetox: thr tuned on tune half, F1/FPR on untouched test half)
|
| 2 |
+
|
| 3 |
+
| set | n | F1@0.5 | tuned thr | test F1@thr | test FPR@thr |
|
| 4 |
+
| --- | --- | --- | --- | --- | --- |
|
| 5 |
+
| textdetox_am | 800 | 0.2974 | 0.74 | 0.031088082901554407 | 0.023255813953488372 |
|
| 6 |
+
| textdetox_ar | 800 | 0.0052 | 0.3 | 0.009852216748768473 | 0.0 |
|
| 7 |
+
| textdetox_de | 800 | 0.5590 | 0.5 | 0.5863874345549738 | 0.36585365853658536 |
|
| 8 |
+
| textdetox_en | 800 | 0.8126 | 0.5 | 0.8243243243243243 | 0.3118811881188119 |
|
| 9 |
+
| textdetox_es | 800 | 0.6183 | 0.5 | 0.6355555555555555 | 0.5396039603960396 |
|
| 10 |
+
| textdetox_fr | 800 | 0.4912 | 0.74 | 0.27848101265822783 | 0.0392156862745098 |
|
| 11 |
+
| textdetox_he | 800 | 0.0293 | 0.3 | 0.06451612903225806 | 0.017857142857142856 |
|
| 12 |
+
| textdetox_hi | 800 | 0.0000 | 0.3 | 0.0 | 0.0 |
|
| 13 |
+
| textdetox_hin | 800 | 0.4521 | 0.73 | 0.17094017094017094 | 0.06532663316582915 |
|
| 14 |
+
| textdetox_it | 800 | 0.5722 | 0.5 | 0.5664160401002506 | 0.41237113402061853 |
|
| 15 |
+
| textdetox_ja | 800 | 0.0000 | 0.3 | 0.0 | 0.0 |
|
| 16 |
+
| textdetox_ru | 800 | 0.5735 | 0.68 | 0.14611872146118723 | 0.05741626794258373 |
|
| 17 |
+
| textdetox_tt | 800 | 0.5819 | 0.5 | 0.5841121495327103 | 0.5336538461538461 |
|
| 18 |
+
| textdetox_uk | 800 | 0.5128 | 0.7 | 0.16666666666666666 | 0.031818181818181815 |
|
| 19 |
+
| textdetox_zh | 800 | 0.0285 | 0.3 | 0.07860262008733625 | 0.03225806451612903 |
|
| 20 |
+
| synth_cs | 300 | 0.9933 | β | β | β |
|
| 21 |
+
| synth_de | 300 | 1.0000 | β | β | β |
|
| 22 |
+
| synth_es | 300 | 1.0000 | β | β | β |
|
| 23 |
+
| synth_fr | 300 | 1.0000 | β | β | β |
|