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.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Barist.4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Barist.4")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Barist.4") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Barist.4", 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 | 0.3577 | 0.73 | 0.12903225806451613 | 0.07075471698113207 |
|
| 6 |
+
| textdetox_ar | 800 | 0.0052 | 0.3 | 0.00970873786407767 | 0.00510204081632653 |
|
| 7 |
+
| textdetox_de | 800 | 0.5575 | 0.5 | 0.558139534883721 | 0.4238095238095238 |
|
| 8 |
+
| textdetox_en | 800 | 0.8131 | 0.5 | 0.8143176733780761 | 0.3382352941176471 |
|
| 9 |
+
| textdetox_es | 800 | 0.6156 | 0.5 | 0.6469248291571753 | 0.47715736040609136 |
|
| 10 |
+
| textdetox_fr | 800 | 0.4856 | 0.74 | 0.2845849802371541 | 0.031746031746031744 |
|
| 11 |
+
| textdetox_he | 800 | 0.0293 | 0.3 | 0.06857142857142856 | 0.01702127659574468 |
|
| 12 |
+
| textdetox_hi | 800 | 0.0000 | 0.3 | 0.0 | 0.0 |
|
| 13 |
+
| textdetox_hin | 800 | 0.4367 | 0.7 | 0.16806722689075632 | 0.08080808080808081 |
|
| 14 |
+
| textdetox_it | 800 | 0.5660 | 0.5 | 0.5378590078328981 | 0.4088669950738916 |
|
| 15 |
+
| textdetox_ja | 800 | 0.0000 | 0.3 | 0.0 | 0.0 |
|
| 16 |
+
| textdetox_ru | 800 | 0.6156 | 0.69 | 0.14746543778801843 | 0.05687203791469194 |
|
| 17 |
+
| textdetox_tt | 800 | 0.6080 | 0.75 | 0.11607142857142858 | 0.05970149253731343 |
|
| 18 |
+
| textdetox_uk | 800 | 0.5526 | 0.7 | 0.20535714285714285 | 0.03864734299516908 |
|
| 19 |
+
| textdetox_zh | 800 | 0.0333 | 0.3 | 0.08411214953271028 | 0.025 |
|
| 20 |
+
| synth_cs | 300 | 0.9899 | 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 |
|