Token Classification
Transformers
Safetensors
English
gpt2
privacy
pii-detection
pii-redaction
sliding-window-attention
rope
swiglu
text-generation-inference
Instructions to use 8Fai/context-filter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 8Fai/context-filter with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="8Fai/context-filter")# Load model directly from transformers import AutoTokenizer, ContextFilterV2 tokenizer = AutoTokenizer.from_pretrained("8Fai/context-filter") model = ContextFilterV2.from_pretrained("8Fai/context-filter", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "vocab_size": 50257, | |
| "hidden_size": 512, | |
| "num_layers": 10, | |
| "num_q_heads": 8, | |
| "num_kv_heads": 4, | |
| "ffn_intermediate": 1792, | |
| "max_seq_len": 32768, | |
| "window_size": 512, | |
| "rope_theta": 500000.0, | |
| "dropout": 0.05, | |
| "entity_types": [ | |
| "PERSON", | |
| "EMAIL", | |
| "PHONE", | |
| "ADDRESS", | |
| "SSN", | |
| "CREDITCARD", | |
| "IP", | |
| "DATE", | |
| "ORG", | |
| "USERNAME", | |
| "PASSPORT", | |
| "DRIVERSLICENSE" | |
| ], | |
| "num_train_examples": 500000, | |
| "num_val_examples": 8000, | |
| "batch_size": 64, | |
| "grad_accum": 1, | |
| "max_train_length": 384, | |
| "learning_rate": 0.0004, | |
| "warmup_steps": 800, | |
| "max_epochs": 3, | |
| "weight_decay": 0.01, | |
| "max_grad_norm": 1.0, | |
| "label_smoothing": 0.05, | |
| "focal_gamma": 2.0, | |
| "seed": 42, | |
| "output_dir": "/vol/context_filter_v2", | |
| "architectures": [ | |
| "ContextFilterV2" | |
| ], | |
| "model_type": "gpt2", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.0", | |
| "id2label": { | |
| "0": "O", | |
| "1": "B-PERSON", | |
| "2": "I-PERSON", | |
| "3": "B-EMAIL", | |
| "4": "I-EMAIL", | |
| "5": "B-PHONE", | |
| "6": "I-PHONE", | |
| "7": "B-ADDRESS", | |
| "8": "I-ADDRESS", | |
| "9": "B-SSN", | |
| "10": "I-SSN", | |
| "11": "B-CREDITCARD", | |
| "12": "I-CREDITCARD", | |
| "13": "B-IP", | |
| "14": "I-IP", | |
| "15": "B-DATE", | |
| "16": "I-DATE", | |
| "17": "B-ORG", | |
| "18": "I-ORG", | |
| "19": "B-USERNAME", | |
| "20": "I-USERNAME", | |
| "21": "B-PASSPORT", | |
| "22": "I-PASSPORT", | |
| "23": "B-DRIVERSLICENSE", | |
| "24": "I-DRIVERSLICENSE" | |
| }, | |
| "label2id": { | |
| "O": "0", | |
| "B-PERSON": "1", | |
| "I-PERSON": "2", | |
| "B-EMAIL": "3", | |
| "I-EMAIL": "4", | |
| "B-PHONE": "5", | |
| "I-PHONE": "6", | |
| "B-ADDRESS": "7", | |
| "I-ADDRESS": "8", | |
| "B-SSN": "9", | |
| "I-SSN": "10", | |
| "B-CREDITCARD": "11", | |
| "I-CREDITCARD": "12", | |
| "B-IP": "13", | |
| "I-IP": "14", | |
| "B-DATE": "15", | |
| "I-DATE": "16", | |
| "B-ORG": "17", | |
| "I-ORG": "18", | |
| "B-USERNAME": "19", | |
| "I-USERNAME": "20", | |
| "B-PASSPORT": "21", | |
| "I-PASSPORT": "22", | |
| "B-DRIVERSLICENSE": "23", | |
| "I-DRIVERSLICENSE": "24" | |
| } | |
| } |