Token Classification
Transformers
Safetensors
Moroccan Arabic
Arabic
bert
part-of-speech
pos-tagging
moroccan-darija
darija
low-resource-languages
Eval Results (legacy)
Instructions to use TypicaAI/DarijaPOSTagger with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TypicaAI/DarijaPOSTagger with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="TypicaAI/DarijaPOSTagger")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("TypicaAI/DarijaPOSTagger") model = AutoModelForTokenClassification.from_pretrained("TypicaAI/DarijaPOSTagger") - Notebooks
- Google Colab
- Kaggle
| { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "BertForTokenClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": null, | |
| "classifier_dropout": null, | |
| "cls_token": "[CLS]", | |
| "do_lower_case": true, | |
| "dtype": "float32", | |
| "eos_token_id": null, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "O", | |
| "1": "ADJ", | |
| "2": "ADV", | |
| "3": "CASE", | |
| "4": "CONJ", | |
| "5": "DET", | |
| "6": "FUT_PART", | |
| "7": "NEG_PART", | |
| "8": "NOUN", | |
| "9": "NSUFF", | |
| "10": "PART", | |
| "11": "PREP", | |
| "12": "PROG_PART", | |
| "13": "PRON", | |
| "14": "V" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "label2id": { | |
| "ADJ": 1, | |
| "ADV": 2, | |
| "CASE": 3, | |
| "CONJ": 4, | |
| "DET": 5, | |
| "FUT_PART": 6, | |
| "NEG_PART": 7, | |
| "NOUN": 8, | |
| "NSUFF": 9, | |
| "O": 0, | |
| "PART": 10, | |
| "PREP": 11, | |
| "PROG_PART": 12, | |
| "PRON": 13, | |
| "V": 14 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "mask_token": "[MASK]", | |
| "max_len": 128, | |
| "max_position_embeddings": 512, | |
| "model_max_length": 128, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token": "[PAD]", | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "sep_token": "[SEP]", | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.12.1", | |
| "type_vocab_size": 2, | |
| "unk_token": "[UNK]", | |
| "use_cache": true, | |
| "vocab_size": 80000 | |
| } | |