Text Classification
Transformers
Safetensors
English
modernbert
ai-text-detection
idea-provenance
text-embeddings-inference
Instructions to use rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem") model = AutoModelForSequenceClassification.from_pretrained("rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download thresholds.json from rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem: direct link, hf CLI and curl.
- Browser
- Download file 3.55 kB
-
https://huggingface.co/rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem/resolve/main/thresholds.json
- Command line
-
hf download hf://rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem/thresholds.json
-
curl -L -o thresholds.json https://huggingface.co/rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem/resolve/main/thresholds.json
3.55 kB
| { | |
| "model": "rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem", | |
| "input": "outline items, pooled per document by logit mean", | |
| "flag_rule": "flag the document as AI when P(human) < cut", | |
| "calibration": { | |
| "data": "WildOutlines, calibration split (human documents only)", | |
| "scores_from": "the training run's stored predictions on the calibration split", | |
| "n_humans": 79999, | |
| "n_per_format": { | |
| "Academic Writing": 9999, | |
| "Creative Writing": 10000, | |
| "Knowledge Article": 10000, | |
| "News Article": 10000, | |
| "Nonfiction Writing": 10000, | |
| "Personal About Page": 10000, | |
| "Personal Blog": 10000, | |
| "User Reviews": 10000 | |
| } | |
| }, | |
| "method": { | |
| "global": "the target-FPR quantile of P(human) over all calibration humans", | |
| "per_group": "the group's own quantile, shrunk toward the global cut with weight n / (n + 2500)", | |
| "min_group_humans": 200, | |
| "estimability": "a cut at FPR q is given only when q * n >= 25 calibration humans", | |
| "missing_cut": "no cut for a group means none could be estimated; do not substitute the global cut" | |
| }, | |
| "fpr_targets": [ | |
| 0.001, | |
| 0.005, | |
| 0.01, | |
| 0.02, | |
| 0.05, | |
| 0.1, | |
| 0.2 | |
| ], | |
| "global": { | |
| "0.001": 0.04404379761259952, | |
| "0.005": 0.12205192356750667, | |
| "0.01": 0.1906184377087428, | |
| "0.02": 0.27399145838356886, | |
| "0.05": 0.40829174191907486, | |
| "0.1": 0.5295915983924087, | |
| "0.2": 0.6643099841853771 | |
| }, | |
| "per_format": { | |
| "0.005": { | |
| "Academic Writing": 0.1807748612889961, | |
| "Creative Writing": 0.24713468732885646, | |
| "Knowledge Article": 0.10024635181124168, | |
| "News Article": 0.14287497641549482, | |
| "Nonfiction Writing": 0.06980665613022045, | |
| "Personal About Page": 0.21159626808248722, | |
| "Personal Blog": 0.1889627444611509, | |
| "User Reviews": 0.11691633894464498 | |
| }, | |
| "0.01": { | |
| "Academic Writing": 0.23996633333182593, | |
| "Creative Writing": 0.3365072065237298, | |
| "Knowledge Article": 0.14883988016267796, | |
| "News Article": 0.2009178899326695, | |
| "Nonfiction Writing": 0.10862978000095241, | |
| "Personal About Page": 0.2917278975191723, | |
| "Personal Blog": 0.24748830566272112, | |
| "User Reviews": 0.17994967066660927 | |
| }, | |
| "0.02": { | |
| "Academic Writing": 0.3183908255492838, | |
| "Creative Writing": 0.4448707131619425, | |
| "Knowledge Article": 0.21691485843196545, | |
| "News Article": 0.26932684635020876, | |
| "Nonfiction Writing": 0.16810775975620385, | |
| "Personal About Page": 0.3945595380604795, | |
| "Personal Blog": 0.3184763547505225, | |
| "User Reviews": 0.25976622502192565 | |
| }, | |
| "0.05": { | |
| "Academic Writing": 0.43266123799920986, | |
| "Creative Writing": 0.5798750487791098, | |
| "Knowledge Article": 0.34602680302674643, | |
| "News Article": 0.3788878608747563, | |
| "Nonfiction Writing": 0.31755950860408005, | |
| "Personal About Page": 0.5422821993351401, | |
| "Personal Blog": 0.4424141255937674, | |
| "User Reviews": 0.3878019815644175 | |
| }, | |
| "0.1": { | |
| "Academic Writing": 0.5488365257282245, | |
| "Creative Writing": 0.689598699411905, | |
| "Knowledge Article": 0.45333259213646376, | |
| "News Article": 0.4869954798371294, | |
| "Nonfiction Writing": 0.45875589553065843, | |
| "Personal About Page": 0.6498729757986291, | |
| "Personal Blog": 0.5476612646714732, | |
| "User Reviews": 0.5156945701573492 | |
| }, | |
| "0.2": { | |
| "Academic Writing": 0.6853088277724884, | |
| "Creative Writing": 0.7926475261681198, | |
| "Knowledge Article": 0.5828659789659236, | |
| "News Article": 0.6067655661202837, | |
| "Nonfiction Writing": 0.6216511924727005, | |
| "Personal About Page": 0.7620108865901676, | |
| "Personal Blog": 0.6814026840900511, | |
| "User Reviews": 0.6533549177048715 | |
| } | |
| }, | |
| "pooling": "logit_mean" | |
| } | |