Text Classification
Model2Vec
Safetensors
English
pubguard
document-classification
scientific-papers
ai-detection
toxicity-detection
pubverse
publication-screening
quality-control
Instructions to use jimnoneill/pub-guard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Model2Vec
How to use jimnoneill/pub-guard with Model2Vec:
from model2vec import StaticModel model = StaticModel.from_pretrained("jimnoneill/pub-guard") embeddings = model.encode(["It's dangerous to go alone!", "It's a secret to everybody."]) print(embeddings.shape) - Notebooks
- Google Colab
- Kaggle
Download config.json from jimnoneill/pub-guard: direct link, hf CLI and curl.
- Browser
- Download file 938 Bytes
-
https://huggingface.co/jimnoneill/pub-guard/resolve/main/config.json
- Command line
-
hf download hf://jimnoneill/pub-guard/config.json
-
curl -L -o config.json https://huggingface.co/jimnoneill/pub-guard/resolve/main/config.json
938 Bytes
| { | |
| "model_type": "pubguard", | |
| "architecture": "multi_head_linear", | |
| "embedding_backbone": "minishlab/potion-base-32M", | |
| "embedding_dim": 512, | |
| "structural_features": 14, | |
| "heads": { | |
| "doc_type": { | |
| "classes": [ | |
| "scientific_paper", | |
| "poster", | |
| "abstract_only", | |
| "junk" | |
| ], | |
| "num_classes": 4, | |
| "input_dim": 526, | |
| "accuracy": 0.997, | |
| "head_file": "models/head_doc_type.npz" | |
| }, | |
| "ai_detect": { | |
| "classes": [ | |
| "human", | |
| "ai_generated" | |
| ], | |
| "num_classes": 2, | |
| "input_dim": 512, | |
| "accuracy": 0.834, | |
| "head_file": "models/head_ai_detect.npz" | |
| }, | |
| "toxicity": { | |
| "classes": [ | |
| "clean", | |
| "toxic" | |
| ], | |
| "num_classes": 2, | |
| "input_dim": 512, | |
| "accuracy": 0.847, | |
| "head_file": "models/head_toxicity.npz" | |
| } | |
| }, | |
| "classifier": "LogisticRegression", | |
| "library_name": "model2vec" | |
| } |