Instructions to use gliner-community/gliner_large-v2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER
How to use gliner-community/gliner_large-v2.5 with GLiNER:
from gliner import GLiNER model = GLiNER.from_pretrained("gliner-community/gliner_large-v2.5") 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 gliner-community/gliner_large-v2.5: direct link, hf CLI and curl.
- Browser
- Download file 676 Bytes
-
https://huggingface.co/gliner-community/gliner_large-v2.5/resolve/3b3bcaeacf8b0b63f957564c069f06b9a0585f8e/gliner_config.json
- Command line
-
hf download hf://gliner-community/gliner_large-v2.5@3b3bcaeacf8b0b63f957564c069f06b9a0585f8e/gliner_config.json
-
curl -L -o gliner_config.json https://huggingface.co/gliner-community/gliner_large-v2.5/resolve/3b3bcaeacf8b0b63f957564c069f06b9a0585f8e/gliner_config.json
676 Bytes
| { | |
| "class_token_index": 128001, | |
| "dropout": 0.4, | |
| "encoder_config": null, | |
| "ent_token": "<<ENT>>", | |
| "fine_tune": true, | |
| "has_rnn": true, | |
| "hidden_size": 768, | |
| "label_smoothing": 0.0, | |
| "loss_alpha": 0.8, | |
| "loss_gamma": 0, | |
| "loss_reduction": "sum", | |
| "max_len": 768, | |
| "max_neg_type_ratio": 1, | |
| "max_types": 30, | |
| "max_width": 12, | |
| "model_name": "microsoft/deberta-v3-large", | |
| "model_type": "gliner", | |
| "name": "span level gliner", | |
| "random_drop": true, | |
| "sep_token": "<<SEP>>", | |
| "shuffle_types": true, | |
| "span_mode": "markerV0", | |
| "subtoken_pooling": "first", | |
| "transformers_version": "4.40.2", | |
| "vocab_size": 128003, | |
| "words_splitter_type": "whitespace" | |
| } | |