Token Classification
Transformers
Safetensors
mt5
named-entity-recognition
luganda
african-language
pii-detection
Generated from Trainer
Eval Results (legacy)
Instructions to use Beijuka/mt5-base-luganda-ner-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Beijuka/mt5-base-luganda-ner-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Beijuka/mt5-base-luganda-ner-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Beijuka/mt5-base-luganda-ner-v1") model = AutoModelForTokenClassification.from_pretrained("Beijuka/mt5-base-luganda-ner-v1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "MT5ForTokenClassification" | |
| ], | |
| "classifier_dropout": 0.0, | |
| "ctc_zero_infinity": true, | |
| "d_ff": 2048, | |
| "d_kv": 64, | |
| "d_model": 768, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "id2label": { | |
| "0": "B-DATE", | |
| "1": "I-DATE", | |
| "2": "L-DATE", | |
| "3": "U-DATE", | |
| "4": "B-GOVT_ID", | |
| "5": "I-GOVT_ID", | |
| "6": "L-GOVT_ID", | |
| "7": "U-GOVT_ID", | |
| "8": "B-LOCATION", | |
| "9": "I-LOCATION", | |
| "10": "L-LOCATION", | |
| "11": "U-LOCATION", | |
| "12": "B-NORP", | |
| "13": "I-NORP", | |
| "14": "L-NORP", | |
| "15": "U-NORP", | |
| "16": "B-ORG", | |
| "17": "I-ORG", | |
| "18": "L-ORG", | |
| "19": "U-ORG", | |
| "20": "B-PERSON", | |
| "21": "I-PERSON", | |
| "22": "L-PERSON", | |
| "23": "U-PERSON", | |
| "24": "B-USERID", | |
| "25": "I-USERID", | |
| "26": "L-USERID", | |
| "27": "U-USERID", | |
| "28": "O" | |
| }, | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": false, | |
| "is_gated_act": true, | |
| "label2id": { | |
| "B-DATE": 0, | |
| "B-GOVT_ID": 4, | |
| "B-LOCATION": 8, | |
| "B-NORP": 12, | |
| "B-ORG": 16, | |
| "B-PERSON": 20, | |
| "B-USERID": 24, | |
| "I-DATE": 1, | |
| "I-GOVT_ID": 5, | |
| "I-LOCATION": 9, | |
| "I-NORP": 13, | |
| "I-ORG": 17, | |
| "I-PERSON": 21, | |
| "I-USERID": 25, | |
| "L-DATE": 2, | |
| "L-GOVT_ID": 6, | |
| "L-LOCATION": 10, | |
| "L-NORP": 14, | |
| "L-ORG": 18, | |
| "L-PERSON": 22, | |
| "L-USERID": 26, | |
| "O": 28, | |
| "U-DATE": 3, | |
| "U-GOVT_ID": 7, | |
| "U-LOCATION": 11, | |
| "U-NORP": 15, | |
| "U-ORG": 19, | |
| "U-PERSON": 23, | |
| "U-USERID": 27 | |
| }, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "mt5", | |
| "num_decoder_layers": 12, | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "T5Tokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.55.4", | |
| "use_cache": false, | |
| "vocab_size": 250112 | |
| } | |