Instructions to use DeepMount00/universal_ner_ita with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER
How to use DeepMount00/universal_ner_ita with GLiNER:
from gliner import GLiNER model = GLiNER.from_pretrained("DeepMount00/universal_ner_ita") text = "Cristiano Ronaldo dos Santos Aveiro was born on 5 February 1985 in Funchal, Madeira, Portugal." labels = ["person", "date", "location"] entities = model.predict_entities(text, labels) for entity in entities: print(entity["text"], "=>", entity["label"]) - Notebooks
- Google Colab
- Kaggle
Download gliner_config.json from DeepMount00/universal_ner_ita: direct link, hf CLI and curl.
- Browser
- Download file 599 Bytes
-
https://huggingface.co/DeepMount00/universal_ner_ita/resolve/main/gliner_config.json
- Command line
-
hf download hf://DeepMount00/universal_ner_ita/gliner_config.json
-
curl -L -o gliner_config.json https://huggingface.co/DeepMount00/universal_ner_ita/resolve/main/gliner_config.json
599 Bytes
| { | |
| "lr_encoder": "1e-5", | |
| "lr_others": "5e-5", | |
| "num_steps": 100000, | |
| "warmup_ratio": 0.1, | |
| "train_batch_size": 8, | |
| "eval_every": 900000, | |
| "max_width": 10, | |
| "model_name": "dbmdz/bert-base-italian-xxl-cased", | |
| "fine_tune": true, | |
| "subtoken_pooling": "first", | |
| "hidden_size": 768, | |
| "span_mode": "marker", | |
| "dropout": 0.4, | |
| "root_dir": "ablation_backbone", | |
| "train_data": "dataset/train.json", | |
| "prev_path": "none", | |
| "size_sup": -1, | |
| "max_types": 25, | |
| "shuffle_types": true, | |
| "random_drop": true, | |
| "max_neg_type_ratio": 1, | |
| "max_len": 384, | |
| "name": "large", | |
| "log_dir": "logs" | |
| } |