Text Classification
Transformers
Safetensors
English
modernbert
ai-text-detection
prose-provenance
text-embeddings-inference
Instructions to use rishanthrajendhran/ProseLens-ModernBERT-L with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rishanthrajendhran/ProseLens-ModernBERT-L with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="rishanthrajendhran/ProseLens-ModernBERT-L")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("rishanthrajendhran/ProseLens-ModernBERT-L") model = AutoModelForSequenceClassification.from_pretrained("rishanthrajendhran/ProseLens-ModernBERT-L", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download thresholds.json from rishanthrajendhran/ProseLens-ModernBERT-L: direct link, hf CLI and curl.
- Browser
- Download file 2.69 kB
-
https://huggingface.co/rishanthrajendhran/ProseLens-ModernBERT-L/resolve/main/thresholds.json
- Command line
-
hf download hf://rishanthrajendhran/ProseLens-ModernBERT-L/thresholds.json
-
curl -L -o thresholds.json https://huggingface.co/rishanthrajendhran/ProseLens-ModernBERT-L/resolve/main/thresholds.json
2.69 kB
| { | |
| "model": "rishanthrajendhran/ProseLens-ModernBERT-L", | |
| "input": "document", | |
| "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": 80000, | |
| "n_per_format": { | |
| "Academic Writing": 10000, | |
| "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 | |
| ], | |
| "global": { | |
| "0.001": 0.005766863141208887, | |
| "0.005": 0.043511959370225665, | |
| "0.01": 0.18790396720170977, | |
| "0.02": 0.8414405298233032, | |
| "0.05": 0.9982767522335052 | |
| }, | |
| "per_format": { | |
| "0.005": { | |
| "Academic Writing": 0.48511697150394323, | |
| "Creative Writing": 0.7774797902218998, | |
| "Knowledge Article": 0.0264915764220059, | |
| "News Article": 0.042131727289408456, | |
| "Nonfiction Writing": 0.016996091064065695, | |
| "Personal About Page": 0.08180167488381268, | |
| "Personal Blog": 0.42620853902027017, | |
| "User Reviews": 0.24418430317565804 | |
| }, | |
| "0.01": { | |
| "Academic Writing": 0.8101551976799966, | |
| "Creative Writing": 0.83455596023798, | |
| "Knowledge Article": 0.07479736334085464, | |
| "News Article": 0.16216902357339863, | |
| "Nonfiction Writing": 0.0544652368426323, | |
| "Personal About Page": 0.36414291030168533, | |
| "Personal Blog": 0.7883320108056069, | |
| "User Reviews": 0.7249871950745583 | |
| }, | |
| "0.02": { | |
| "Academic Writing": 0.9664362020492554, | |
| "Creative Writing": 0.9677177896499634, | |
| "Knowledge Article": 0.28712427091598514, | |
| "News Article": 0.6937795658111573, | |
| "Nonfiction Writing": 0.22745220160484314, | |
| "Personal About Page": 0.9371422376632691, | |
| "Personal Blog": 0.9637664785385132, | |
| "User Reviews": 0.9604384603500367 | |
| }, | |
| "0.05": { | |
| "Academic Writing": 0.9994967925548554, | |
| "Creative Writing": 0.999563969373703, | |
| "Knowledge Article": 0.9463144671916961, | |
| "News Article": 0.9944453680515289, | |
| "Nonfiction Writing": 0.8933786427974701, | |
| "Personal About Page": 0.9992063510417939, | |
| "Personal Blog": 0.9993082511425019, | |
| "User Reviews": 0.999339975118637 | |
| } | |
| } | |
| } | |