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
Download reports/gates.json from KucLab/Barist.1: direct link, hf CLI and curl.
- Browser
- Download file 2.8 kB
-
https://huggingface.co/KucLab/Barist.1/resolve/main/reports/gates.json
- Command line
-
hf download hf://KucLab/Barist.1/reports/gates.json
-
curl -L -o gates.json https://huggingface.co/KucLab/Barist.1/resolve/main/reports/gates.json
2.8 kB
| { | |
| "tag": "Barist.1.1", | |
| "checkpoint": "checkpoints_b1q/best.pt", | |
| "censer9": "/home/tvadmin/censer.9/checkpoints/best.pt", | |
| "set": "heldout2 = data/mustcatch_heldout2.jsonl (72 rows after dedup purge, max 5-gram overlap 0.75)", | |
| "gates": [ | |
| { | |
| "gate": "heldout2_model_only", | |
| "censer.9": "44/61", | |
| "Barist.1.1": "45/61", | |
| "minimum": "44/61", | |
| "target": "52/61", | |
| "pass": true | |
| }, | |
| { | |
| "gate": "heldout2_with_prefilter", | |
| "censer.9": "49/61", | |
| "Barist.1.1": "49/61", | |
| "minimum": "49/61", | |
| "target": "58/61", | |
| "pass": true | |
| }, | |
| { | |
| "gate": "heldout2_benign_fp", | |
| "censer.9": "4/11", | |
| "Barist.1.1": "2/11", | |
| "minimum": "2/11", | |
| "target": "1/11", | |
| "pass": true | |
| }, | |
| { | |
| "gate": "cs_benign_fpr_raw", | |
| "censer.9": 0.2783, | |
| "Barist.1.1": 0.1, | |
| "minimum": 0.05, | |
| "target": 0.03, | |
| "pass": false | |
| }, | |
| { | |
| "gate": "cs_benign_fpr@cs_thr", | |
| "censer.9": 0.2522, | |
| "Barist.1.1": 0.0609, | |
| "minimum": 0.05, | |
| "target": 0.03, | |
| "pass": false | |
| }, | |
| { | |
| "gate": "hardneg_fp", | |
| "censer.9": "6/44", | |
| "Barist.1.1": "5/44", | |
| "minimum": "3/44", | |
| "target": "1/44", | |
| "pass": false | |
| }, | |
| { | |
| "gate": "train_must_catch", | |
| "censer.9": "84/88", | |
| "Barist.1.1": "82/88", | |
| "minimum": "84/88", | |
| "target": "86/88", | |
| "pass": false | |
| }, | |
| { | |
| "gate": "test_f1", | |
| "censer.9": 0.8239, | |
| "Barist.1.1": 0.8238, | |
| "minimum": 0.83, | |
| "target": 0.849, | |
| "pass": false | |
| }, | |
| { | |
| "gate": "test_recall", | |
| "censer.9": 0.7987, | |
| "Barist.1.1": 0.7909, | |
| "minimum": 0.8, | |
| "target": 0.83, | |
| "pass": false | |
| }, | |
| { | |
| "gate": "test_precision", | |
| "censer.9": 0.8508, | |
| "Barist.1.1": 0.8595, | |
| "minimum": 0.85, | |
| "target": 0.86, | |
| "pass": true | |
| }, | |
| { | |
| "gate": "user_benign_fp", | |
| "censer.9": "34/41", | |
| "Barist.1.1": "14/41", | |
| "minimum": "3/43", | |
| "target": "1/43", | |
| "pass": false | |
| }, | |
| { | |
| "gate": "ece_calibrated", | |
| "censer.9": 0.02606656088259697, | |
| "Barist.1.1": 0.02606656088259697, | |
| "minimum": 0.035, | |
| "target": 0.03, | |
| "pass": true | |
| }, | |
| { | |
| "gate": "onnx_max_abs_diff", | |
| "censer.9": 0.0001, | |
| "Barist.1.1": 0.0001, | |
| "minimum": 0.001, | |
| "target": 0.0001, | |
| "pass": true | |
| }, | |
| { | |
| "gate": "regex_gate_hard_fp", | |
| "censer.9": 0, | |
| "Barist.1.1": 0, | |
| "minimum": 0, | |
| "target": 0, | |
| "pass": true | |
| }, | |
| { | |
| "gate": "heldout2_dedup_max_overlap", | |
| "censer.9": 0.75, | |
| "Barist.1.1": 0.75, | |
| "minimum": 0.8, | |
| "target": 0.5, | |
| "pass": true | |
| } | |
| ], | |
| "all_pass": false | |
| } |