Text Classification
Transformers
Safetensors
multilingual
distilbert
phishing
email-security
text-embeddings-inference
Instructions to use eugenioderodev/fishstop-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eugenioderodev/fishstop-bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="eugenioderodev/fishstop-bert")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("eugenioderodev/fishstop-bert") model = AutoModelForSequenceClassification.from_pretrained("eugenioderodev/fishstop-bert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "activation": "gelu", | |
| "architectures": [ | |
| "DistilBertForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bos_token_id": null, | |
| "dim": 768, | |
| "dropout": 0.1, | |
| "dtype": "float32", | |
| "eos_token_id": null, | |
| "fishstop_chunk_aggregation": "maximum_positive_logit_margin", | |
| "fishstop_dataset_sha256": "c89e1f5d2bb92b5a5dd5beb8a235a798932ed19eb9d75c2f740a94b5fd450816", | |
| "fishstop_positive_label_id": 1, | |
| "fishstop_preprocessing": "src.bert_input.normalize_bert_text", | |
| "fishstop_split_strategy": "campaign_grouped_random_stratified_70_10_20", | |
| "hidden_dim": 3072, | |
| "id2label": { | |
| "0": "LEGITIMATE", | |
| "1": "MALICIOUS" | |
| }, | |
| "initializer_range": 0.02, | |
| "label2id": { | |
| "LEGITIMATE": 0, | |
| "MALICIOUS": 1 | |
| }, | |
| "max_position_embeddings": 512, | |
| "model_type": "distilbert", | |
| "n_heads": 12, | |
| "n_layers": 6, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "qa_dropout": 0.1, | |
| "seq_classif_dropout": 0.2, | |
| "sinusoidal_pos_embds": false, | |
| "tie_weights_": true, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.13.1", | |
| "use_cache": false, | |
| "vocab_size": 119547 | |
| } | |