| language: en | |
| library_name: transformers | |
| tags: | |
| - multilabel-classification | |
| - deberta-v3 | |
| - opp115 | |
| metrics: | |
| - macro_f1 | |
| - micro_f1 | |
| - weighted_f1 | |
| - macro_precision | |
| - macro_recall | |
| # DeBERTaV3 Base — OPP115 Multilabel (v2) | |
| Fine-tuned DeBERTaV3 model for multi-label classification on the OPP115 dataset. | |
| ## 📊 Evaluation Metrics | |
| | Metric | Score | | |
| |--------|--------| | |
| | **Macro F1** | 0.8092 | | |
| | **Micro F1** | 0.8565 | | |
| | **Weighted F1** | 0.8531 | | |
| | **Macro Precision** | 0.8657 | | |
| | **Macro Recall** | 0.7697 | | |
| ## 🧪 Usage | |
| ```python | |
| from transformers import AutoModelForSequenceClassification, AutoTokenizer | |
| import torch | |
| model = AutoModelForSequenceClassification.from_pretrained("Hacktrix-121/deberta-v3-base-opp115-multilabel-v2") | |
| tokenizer = AutoTokenizer.from_pretrained("Hacktrix-121/deberta-v3-base-opp115-multilabel-v2") | |
| text = "Your input text here" | |
| inputs = tokenizer(text, return_tensors="pt") | |
| logits = model(**inputs).logits | |
| probs = torch.sigmoid(logits) | |