Text Classification
Transformers
PyTorch
Safetensors
inferenceguard-roberta
privacy
inferential-privacy
roberta
multi-task-classification
risk-estimation
integrated-gradients
llm-firewall
Instructions to use AT707/InferenceGuard-Roberta-Risk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AT707/InferenceGuard-Roberta-Risk with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="AT707/InferenceGuard-Roberta-Risk")# pip install -U transformers accelerate # Load model directly from transformers import RobertaRiskClassifier model = RobertaRiskClassifier.from_pretrained("AT707/InferenceGuard-Roberta-Risk", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from AT707/InferenceGuard-Roberta-Risk: direct link, hf CLI and curl.
- Browser
- Download file 442 Bytes
-
https://huggingface.co/AT707/InferenceGuard-Roberta-Risk/resolve/main/config.json
- Command line
-
hf download hf://AT707/InferenceGuard-Roberta-Risk/config.json
-
curl -L -o config.json https://huggingface.co/AT707/InferenceGuard-Roberta-Risk/resolve/main/config.json
442 Bytes
| { | |
| "architectures": [ | |
| "RobertaRiskClassifier" | |
| ], | |
| "attributes": [ | |
| "age", | |
| "location", | |
| "occupation", | |
| "education" | |
| ], | |
| "base_model_name": "roberta-base", | |
| "classifier_dropout": 0.1, | |
| "dtype": "float32", | |
| "hidden_size": 768, | |
| "model_type": "inferenceguard-roberta", | |
| "num_classes_per_head": 1, | |
| "num_heads": 4, | |
| "temperature_values": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "transformers_version": "5.20.2" | |
| } | |