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.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Barist.6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Barist.6")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Barist.6") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Barist.6", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download reports/calibration.json from KucLab/Barist.6: direct link, hf CLI and curl.
- Browser
- Download file 2.8 kB
-
https://huggingface.co/KucLab/Barist.6/resolve/main/reports/calibration.json
- Command line
-
hf download hf://KucLab/Barist.6/reports/calibration.json
-
curl -L -o calibration.json https://huggingface.co/KucLab/Barist.6/resolve/main/reports/calibration.json
2.8 kB
| { | |
| "checkpoint": "checkpoints_b6b/best.pt", | |
| "temperature": 0.6141347587109078, | |
| "val_n": 6585, | |
| "binary_ece_raw": 0.07447951763625069, | |
| "binary_ece": 0.021661004990066318, | |
| "catval_n": 3542, | |
| "categories": { | |
| "violence": { | |
| "best_threshold": 0.5, | |
| "f1_at_best": 0.25180897250361794, | |
| "ece": 0.2091648375795688, | |
| "prevalence": 0.052795031055900624, | |
| "experimental": true | |
| }, | |
| "weapons_explosives": { | |
| "best_threshold": 0.5, | |
| "f1_at_best": 0.2923976608187135, | |
| "ece": 0.04912209152259561, | |
| "prevalence": 0.021456804065499716, | |
| "experimental": true | |
| }, | |
| "drugs": { | |
| "best_threshold": 0.5, | |
| "f1_at_best": 0.05714285714285715, | |
| "ece": 0.055377886751890815, | |
| "prevalence": 0.015527950310559006, | |
| "experimental": true | |
| }, | |
| "hate_harassment": { | |
| "best_threshold": 0.4, | |
| "f1_at_best": 0.9226350057449253, | |
| "ece": 0.20687973018386466, | |
| "prevalence": 0.7532467532467533, | |
| "experimental": false | |
| }, | |
| "sexual_abuse": { | |
| "best_threshold": 0.3, | |
| "f1_at_best": 0.0, | |
| "ece": 0.09318666425405903, | |
| "prevalence": 0.020045172219085264, | |
| "experimental": true, | |
| "note": "fixed 0.3 per review: CSAM/self-harm priority over hate" | |
| }, | |
| "self_harm": { | |
| "best_threshold": 0.3, | |
| "f1_at_best": 0.0, | |
| "ece": 0.04841814441332949, | |
| "prevalence": 0.012140033879164314, | |
| "experimental": true, | |
| "note": "fixed 0.3 per review: CSAM/self-harm priority over hate" | |
| }, | |
| "cybercrime_fraud": { | |
| "best_threshold": 0.5, | |
| "f1_at_best": 0.0, | |
| "ece": 0.06348807147870471, | |
| "prevalence": 0.014680971202710334, | |
| "experimental": true | |
| }, | |
| "jailbreak_injection": { | |
| "best_threshold": 0.5, | |
| "f1_at_best": 0.0, | |
| "ece": 0.049857524966660745, | |
| "prevalence": 0.01355166572557877, | |
| "experimental": true | |
| }, | |
| "illegal_marketplace": { | |
| "best_threshold": 0.5, | |
| "f1_at_best": 0.0, | |
| "ece": 0.03594228076393512, | |
| "prevalence": 0.01129305477131564, | |
| "experimental": true | |
| }, | |
| "other_unsafe": { | |
| "best_threshold": 0.45, | |
| "f1_at_best": 0.5673076923076923, | |
| "ece": 0.025467586545267335, | |
| "prevalence": 0.07001693958215698, | |
| "experimental": false | |
| } | |
| }, | |
| "cat_thresholds": { | |
| "violence": 0.5, | |
| "weapons_explosives": 0.5, | |
| "drugs": 0.5, | |
| "hate_harassment": 0.4, | |
| "sexual_abuse": 0.3, | |
| "self_harm": 0.3, | |
| "cybercrime_fraud": 0.5, | |
| "jailbreak_injection": 0.5, | |
| "illegal_marketplace": 0.5, | |
| "other_unsafe": 0.45 | |
| }, | |
| "cat_experimental": [ | |
| "violence", | |
| "weapons_explosives", | |
| "drugs", | |
| "sexual_abuse", | |
| "self_harm", | |
| "cybercrime_fraud", | |
| "jailbreak_injection", | |
| "illegal_marketplace" | |
| ] | |
| } |