Token Classification
Transformers
Safetensors
Portuguese
bert
feature-extraction
coreference-resolution
meeting-minutes
portuguese
spanbert
administrative-documents
Instructions to use anonymous270126/SpanBERT-Coreference-pt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anonymous270126/SpanBERT-Coreference-pt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="anonymous270126/SpanBERT-Coreference-pt")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("anonymous270126/SpanBERT-Coreference-pt") model = AutoModel.from_pretrained("anonymous270126/SpanBERT-Coreference-pt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download coref_config.json from anonymous270126/SpanBERT-Coreference-pt: direct link, hf CLI and curl.
- Browser
- Download file 442 Bytes
-
https://huggingface.co/anonymous270126/SpanBERT-Coreference-pt/resolve/main/coref_config.json
- Command line
-
hf download hf://anonymous270126/SpanBERT-Coreference-pt/coref_config.json
-
curl -L -o coref_config.json https://huggingface.co/anonymous270126/SpanBERT-Coreference-pt/resolve/main/coref_config.json
442 Bytes
| { | |
| "hidden_size": 768, | |
| "ffnn_dim": 1024, | |
| "max_span_width": 52, | |
| "max_antecedents": 50, | |
| "max_cluster_size": 12, | |
| "dropout": 0.3, | |
| "dist_buckets": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 8, | |
| 16, | |
| 32, | |
| 64 | |
| ], | |
| "ner_union_margin": 0.5, | |
| "min_cluster_score": 0.3, | |
| "epsilon": 0.00040307387826032937, | |
| "domain": "atas municipais portuguesas", | |
| "language": "pt", | |
| "best_val_conll": 0.9187203268708114, | |
| "best_epoch": 13 | |
| } |