Instructions to use IDA-UNISA/PropagandaDetection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IDA-UNISA/PropagandaDetection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="IDA-UNISA/PropagandaDetection")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("IDA-UNISA/PropagandaDetection") model = AutoModelForSequenceClassification.from_pretrained("IDA-UNISA/PropagandaDetection", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download config.json from IDA-UNISA/PropagandaDetection: direct link, hf CLI and curl.
- Browser
- Download file 749 Bytes
-
https://huggingface.co/IDA-UNISA/PropagandaDetection/resolve/main/config.json
- Command line
-
hf download hf://IDA-UNISA/PropagandaDetection/config.json
-
curl -L -o config.json https://huggingface.co/IDA-UNISA/PropagandaDetection/resolve/main/config.json
749 Bytes
| { | |
| "_name_or_path": "distilbert-base-uncased", | |
| "activation": "gelu", | |
| "architectures": [ | |
| "DistilBertForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.1, | |
| "dim": 768, | |
| "dropout": 0.1, | |
| "hidden_dim": 3072, | |
| "id2label": { | |
| "0": "NO_PROPAGANDA", | |
| "1": "PROPAGANDA" | |
| }, | |
| "initializer_range": 0.02, | |
| "label2id": { | |
| "NO_PROPAGANDA": 0, | |
| "PROPAGANDA": 1 | |
| }, | |
| "max_position_embeddings": 512, | |
| "model_type": "distilbert", | |
| "n_heads": 12, | |
| "n_layers": 6, | |
| "pad_token_id": 0, | |
| "problem_type": "single_label_classification", | |
| "qa_dropout": 0.1, | |
| "seq_classif_dropout": 0.2, | |
| "sinusoidal_pos_embds": false, | |
| "tie_weights_": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.25.1", | |
| "vocab_size": 30522 | |
| } | |