Downloads · 30 days
9
0% of all-time downloads
deprem-ml/deprem-ner-mdebertav3
deprem-ner-mdebertav3 is a token classification model from deprem-ml. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
- Precision: 0.711819 - Recall: 0.783626 - F1: 0.745999 - Accuracy: 0.933360
Downloads · 30 days
9
0% of all-time downloads
All-time downloads
21.4K
Public
Repo size
4.5 GB
Likes
4
Public
Click a slice to open those files.
.pt2.2 GB · 66%
From the Hugging Face model README
evaluation_strategy="epoch"
save_strategy="epoch"
load_best_model_at_end=True
learning_rate=3e-5
per_device_train_batch_size=8
per_device_eval_batch_size=16
num_train_epochs=15
weight_decay=0.01
seed=42
Bu model depremde enkaz altında kalan kişilerin bildirimlerinden sokak, il, ilçe gibi bilgileri çekmeye çalıştık.
Örnek girdiler:
Verdiği çıktılar:
[
{
"entity_group": "mahalle",
"score": 0.8160411715507507,
"word": "Akevler mahallesi",
"start": 14,
"end": 31
},
{
"entity_group": "sokak",
"score": 0.940501868724823,
"word": "Rüzgar sokak",
"start": 32,
"end": 44
},
{
"entity_group": "Apartman/Site",
"score": 0.8081040978431702,
"word": "Tuncay apartmanı",
"start": 45,
"end": 61
},
{
"entity_group": "ilce",
"score": 0.854024350643158,
"word": "Antakya",
"start": 72,
"end": 79
}
]
Bu modeli Hugging Face Hub'daki diğer modellerle karşılaştırdık, örnek 30 input'ta sonuçları bu repository'de bulabilirsiniz.