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.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Barist.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Barist.1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Barist.1") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Barist.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add report calibration.json
Browse files- reports/calibration.json +23 -23
reports/calibration.json
CHANGED
|
@@ -1,78 +1,78 @@
|
|
| 1 |
{
|
| 2 |
-
"checkpoint": "
|
| 3 |
-
"temperature": 0.
|
| 4 |
"val_n": 6585,
|
| 5 |
-
"binary_ece_raw": 0.
|
| 6 |
-
"binary_ece": 0.
|
| 7 |
"catval_n": 3542,
|
| 8 |
"categories": {
|
| 9 |
"violence": {
|
| 10 |
"best_threshold": 0.5,
|
| 11 |
-
"f1_at_best": 0.
|
| 12 |
-
"ece": 0.
|
| 13 |
"prevalence": 0.052795031055900624,
|
| 14 |
"experimental": true
|
| 15 |
},
|
| 16 |
"weapons_explosives": {
|
| 17 |
"best_threshold": 0.5,
|
| 18 |
-
"f1_at_best": 0.
|
| 19 |
-
"ece": 0.
|
| 20 |
"prevalence": 0.021456804065499716,
|
| 21 |
"experimental": true
|
| 22 |
},
|
| 23 |
"drugs": {
|
| 24 |
"best_threshold": 0.5,
|
| 25 |
-
"f1_at_best": 0.
|
| 26 |
-
"ece": 0.
|
| 27 |
"prevalence": 0.015527950310559006,
|
| 28 |
"experimental": true
|
| 29 |
},
|
| 30 |
"hate_harassment": {
|
| 31 |
"best_threshold": 0.2,
|
| 32 |
-
"f1_at_best": 0.
|
| 33 |
-
"ece": 0.
|
| 34 |
"prevalence": 0.7532467532467533,
|
| 35 |
"experimental": false
|
| 36 |
},
|
| 37 |
"sexual_abuse": {
|
| 38 |
"best_threshold": 0.5,
|
| 39 |
-
"f1_at_best": 0.
|
| 40 |
-
"ece": 0.
|
| 41 |
"prevalence": 0.020045172219085264,
|
| 42 |
"experimental": true
|
| 43 |
},
|
| 44 |
"self_harm": {
|
| 45 |
"best_threshold": 0.5,
|
| 46 |
"f1_at_best": 0.0,
|
| 47 |
-
"ece": 0.
|
| 48 |
"prevalence": 0.012140033879164314,
|
| 49 |
"experimental": true
|
| 50 |
},
|
| 51 |
"cybercrime_fraud": {
|
| 52 |
"best_threshold": 0.5,
|
| 53 |
"f1_at_best": 0.0,
|
| 54 |
-
"ece": 0.
|
| 55 |
"prevalence": 0.014680971202710334,
|
| 56 |
"experimental": true
|
| 57 |
},
|
| 58 |
"jailbreak_injection": {
|
| 59 |
"best_threshold": 0.5,
|
| 60 |
-
"f1_at_best": 0.
|
| 61 |
-
"ece": 0.
|
| 62 |
"prevalence": 0.01355166572557877,
|
| 63 |
"experimental": true
|
| 64 |
},
|
| 65 |
"illegal_marketplace": {
|
| 66 |
"best_threshold": 0.5,
|
| 67 |
"f1_at_best": 0.0,
|
| 68 |
-
"ece": 0.
|
| 69 |
"prevalence": 0.01129305477131564,
|
| 70 |
"experimental": true
|
| 71 |
},
|
| 72 |
"other_unsafe": {
|
| 73 |
-
"best_threshold": 0.
|
| 74 |
-
"f1_at_best": 0.
|
| 75 |
-
"ece": 0.
|
| 76 |
"prevalence": 0.07001693958215698,
|
| 77 |
"experimental": false
|
| 78 |
}
|
|
@@ -87,7 +87,7 @@
|
|
| 87 |
"cybercrime_fraud": 0.5,
|
| 88 |
"jailbreak_injection": 0.5,
|
| 89 |
"illegal_marketplace": 0.5,
|
| 90 |
-
"other_unsafe": 0.
|
| 91 |
},
|
| 92 |
"cat_experimental": [
|
| 93 |
"violence",
|
|
|
|
| 1 |
{
|
| 2 |
+
"checkpoint": "checkpoints_b1q/best.pt",
|
| 3 |
+
"temperature": 0.6698146164414522,
|
| 4 |
"val_n": 6585,
|
| 5 |
+
"binary_ece_raw": 0.06439162811820219,
|
| 6 |
+
"binary_ece": 0.02606655000733749,
|
| 7 |
"catval_n": 3542,
|
| 8 |
"categories": {
|
| 9 |
"violence": {
|
| 10 |
"best_threshold": 0.5,
|
| 11 |
+
"f1_at_best": 0.23984526112185686,
|
| 12 |
+
"ece": 0.16239444964030358,
|
| 13 |
"prevalence": 0.052795031055900624,
|
| 14 |
"experimental": true
|
| 15 |
},
|
| 16 |
"weapons_explosives": {
|
| 17 |
"best_threshold": 0.5,
|
| 18 |
+
"f1_at_best": 0.18556701030927836,
|
| 19 |
+
"ece": 0.041107042356560076,
|
| 20 |
"prevalence": 0.021456804065499716,
|
| 21 |
"experimental": true
|
| 22 |
},
|
| 23 |
"drugs": {
|
| 24 |
"best_threshold": 0.5,
|
| 25 |
+
"f1_at_best": 0.030769230769230767,
|
| 26 |
+
"ece": 0.05274417910668166,
|
| 27 |
"prevalence": 0.015527950310559006,
|
| 28 |
"experimental": true
|
| 29 |
},
|
| 30 |
"hate_harassment": {
|
| 31 |
"best_threshold": 0.2,
|
| 32 |
+
"f1_at_best": 0.91434034416826,
|
| 33 |
+
"ece": 0.21635782092503747,
|
| 34 |
"prevalence": 0.7532467532467533,
|
| 35 |
"experimental": false
|
| 36 |
},
|
| 37 |
"sexual_abuse": {
|
| 38 |
"best_threshold": 0.5,
|
| 39 |
+
"f1_at_best": 0.0,
|
| 40 |
+
"ece": 0.08326548353712206,
|
| 41 |
"prevalence": 0.020045172219085264,
|
| 42 |
"experimental": true
|
| 43 |
},
|
| 44 |
"self_harm": {
|
| 45 |
"best_threshold": 0.5,
|
| 46 |
"f1_at_best": 0.0,
|
| 47 |
+
"ece": 0.04202677538621124,
|
| 48 |
"prevalence": 0.012140033879164314,
|
| 49 |
"experimental": true
|
| 50 |
},
|
| 51 |
"cybercrime_fraud": {
|
| 52 |
"best_threshold": 0.5,
|
| 53 |
"f1_at_best": 0.0,
|
| 54 |
+
"ece": 0.058138416375965396,
|
| 55 |
"prevalence": 0.014680971202710334,
|
| 56 |
"experimental": true
|
| 57 |
},
|
| 58 |
"jailbreak_injection": {
|
| 59 |
"best_threshold": 0.5,
|
| 60 |
+
"f1_at_best": 0.0,
|
| 61 |
+
"ece": 0.04948791098231112,
|
| 62 |
"prevalence": 0.01355166572557877,
|
| 63 |
"experimental": true
|
| 64 |
},
|
| 65 |
"illegal_marketplace": {
|
| 66 |
"best_threshold": 0.5,
|
| 67 |
"f1_at_best": 0.0,
|
| 68 |
+
"ece": 0.033953291705495256,
|
| 69 |
"prevalence": 0.01129305477131564,
|
| 70 |
"experimental": true
|
| 71 |
},
|
| 72 |
"other_unsafe": {
|
| 73 |
+
"best_threshold": 0.29,
|
| 74 |
+
"f1_at_best": 0.6013986013986015,
|
| 75 |
+
"ece": 0.032026222256736,
|
| 76 |
"prevalence": 0.07001693958215698,
|
| 77 |
"experimental": false
|
| 78 |
}
|
|
|
|
| 87 |
"cybercrime_fraud": 0.5,
|
| 88 |
"jailbreak_injection": 0.5,
|
| 89 |
"illegal_marketplace": 0.5,
|
| 90 |
+
"other_unsafe": 0.29
|
| 91 |
},
|
| 92 |
"cat_experimental": [
|
| 93 |
"violence",
|