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 external_eval.json
Browse files- reports/external_eval.json +62 -0
reports/external_eval.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "checkpoints_b4b/best.pt",
|
| 3 |
+
"device": "cuda",
|
| 4 |
+
"results": {
|
| 5 |
+
"toxigen_test": {
|
| 6 |
+
"n": 940,
|
| 7 |
+
"unsafe": 402,
|
| 8 |
+
"at_0.5": {
|
| 9 |
+
"threshold": 0.5,
|
| 10 |
+
"accuracy": 0.6031914893617021,
|
| 11 |
+
"precision": 0.5336426914153132,
|
| 12 |
+
"recall": 0.572139303482587,
|
| 13 |
+
"f1": 0.552220888355342,
|
| 14 |
+
"tp": 230,
|
| 15 |
+
"fp": 201,
|
| 16 |
+
"tn": 337,
|
| 17 |
+
"fn": 172,
|
| 18 |
+
"total": 940
|
| 19 |
+
},
|
| 20 |
+
"best": {
|
| 21 |
+
"threshold": 0.18,
|
| 22 |
+
"accuracy": 0.5117021276595745,
|
| 23 |
+
"precision": 0.46494464944649444,
|
| 24 |
+
"recall": 0.9402985074626866,
|
| 25 |
+
"f1": 0.6222222222222222,
|
| 26 |
+
"tp": 378,
|
| 27 |
+
"fp": 435,
|
| 28 |
+
"tn": 103,
|
| 29 |
+
"fn": 24,
|
| 30 |
+
"total": 940
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"hatexplain_test": {
|
| 34 |
+
"n": 1924,
|
| 35 |
+
"unsafe": 1376,
|
| 36 |
+
"at_0.5": {
|
| 37 |
+
"threshold": 0.5,
|
| 38 |
+
"accuracy": 0.5925155925155925,
|
| 39 |
+
"precision": 0.6957671957671958,
|
| 40 |
+
"recall": 0.7645348837209303,
|
| 41 |
+
"f1": 0.7285318559556788,
|
| 42 |
+
"tp": 1052,
|
| 43 |
+
"fp": 460,
|
| 44 |
+
"tn": 88,
|
| 45 |
+
"fn": 324,
|
| 46 |
+
"total": 1924
|
| 47 |
+
},
|
| 48 |
+
"best": {
|
| 49 |
+
"threshold": 0.05,
|
| 50 |
+
"accuracy": 0.7151767151767152,
|
| 51 |
+
"precision": 0.7151767151767152,
|
| 52 |
+
"recall": 1.0,
|
| 53 |
+
"f1": 0.833939393939394,
|
| 54 |
+
"tp": 1376,
|
| 55 |
+
"fp": 548,
|
| 56 |
+
"tn": 0,
|
| 57 |
+
"fn": 0,
|
| 58 |
+
"total": 1924
|
| 59 |
+
}
|
| 60 |
+
}
|
| 61 |
+
}
|
| 62 |
+
}
|