Token Classification
Transformers
Safetensors
Arabic
bert
named-entity-recognition
ner
arabic
msa
modern-standard-arabic
morocco
moroccan-context
maghreb
biluo
Instructions to use TypicaAI/MagBERT-NER-AR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TypicaAI/MagBERT-NER-AR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="TypicaAI/MagBERT-NER-AR")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("TypicaAI/MagBERT-NER-AR") model = AutoModelForTokenClassification.from_pretrained("TypicaAI/MagBERT-NER-AR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from TypicaAI/MagBERT-NER-AR: direct link, hf CLI and curl.
- Browser
- Download file 2.45 kB
-
https://huggingface.co/TypicaAI/MagBERT-NER-AR/resolve/main/config.json
- Command line
-
hf download hf://TypicaAI/MagBERT-NER-AR/config.json
-
curl -L -o config.json https://huggingface.co/TypicaAI/MagBERT-NER-AR/resolve/main/config.json
2.45 kB
| { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "BertForTokenClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": null, | |
| "classifier_dropout": null, | |
| "dtype": "float32", | |
| "eos_token_id": null, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "B-LOC", | |
| "1": "B-PRODUCT", | |
| "2": "L-PERSON", | |
| "3": "B-CARDINAL", | |
| "4": "L-PERCENT", | |
| "5": "I-PRODUCT", | |
| "6": "I-LAW", | |
| "7": "I-DATE", | |
| "8": "B-NORP", | |
| "9": "L-LOC", | |
| "10": "U-ORG", | |
| "11": "O", | |
| "12": "U-DATE", | |
| "13": "I-EVENT", | |
| "14": "L-GPE", | |
| "15": "U-NORP", | |
| "16": "I-ORG", | |
| "17": "B-LAW", | |
| "18": "I-PERCENT", | |
| "19": "L-DATE", | |
| "20": "B-ORG", | |
| "21": "U-EVENT", | |
| "22": "I-LOC", | |
| "23": "U-GPE", | |
| "24": "L-EVENT", | |
| "25": "B-PERSON", | |
| "26": "B-PERCENT", | |
| "27": "I-PERSON", | |
| "28": "U-CARDINAL", | |
| "29": "I-GPE", | |
| "30": "B-EVENT", | |
| "31": "U-PERSON", | |
| "32": "L-LAW", | |
| "33": "L-NORP", | |
| "34": "L-CARDINAL", | |
| "35": "B-GPE", | |
| "36": "U-ORDINAL", | |
| "37": "B-DATE", | |
| "38": "L-PRODUCT", | |
| "39": "L-ORG", | |
| "40": "U-PRODUCT", | |
| "41": "PAD" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "label2id": { | |
| "B-CARDINAL": 3, | |
| "B-DATE": 37, | |
| "B-EVENT": 30, | |
| "B-GPE": 35, | |
| "B-LAW": 17, | |
| "B-LOC": 0, | |
| "B-NORP": 8, | |
| "B-ORG": 20, | |
| "B-PERCENT": 26, | |
| "B-PERSON": 25, | |
| "B-PRODUCT": 1, | |
| "I-DATE": 7, | |
| "I-EVENT": 13, | |
| "I-GPE": 29, | |
| "I-LAW": 6, | |
| "I-LOC": 22, | |
| "I-ORG": 16, | |
| "I-PERCENT": 18, | |
| "I-PERSON": 27, | |
| "I-PRODUCT": 5, | |
| "L-CARDINAL": 34, | |
| "L-DATE": 19, | |
| "L-EVENT": 24, | |
| "L-GPE": 14, | |
| "L-LAW": 32, | |
| "L-LOC": 9, | |
| "L-NORP": 33, | |
| "L-ORG": 39, | |
| "L-PERCENT": 4, | |
| "L-PERSON": 2, | |
| "L-PRODUCT": 38, | |
| "O": 11, | |
| "PAD": 41, | |
| "U-CARDINAL": 28, | |
| "U-DATE": 12, | |
| "U-EVENT": 21, | |
| "U-GPE": 23, | |
| "U-NORP": 15, | |
| "U-ORDINAL": 36, | |
| "U-ORG": 10, | |
| "U-PERSON": 31, | |
| "U-PRODUCT": 40 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.18.0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |