Turkish Disaster Tweet Classifier
Fine-tuned from dbmdz/bert-base-turkish-cased on a Turkish disaster-response tweet dataset (~30k samples).
Labels
| ID | Label |
|---|---|
| 0 | SituationalUpdate |
| 1 | HelpRequest |
| 2 | Other |
| 3 | AidOffer |
| 4 | OfficialInformation |
| 5 | DamageReport |
Usage
from transformers import pipeline
clf = pipeline("text-classification", model="saribiyiko/bert-turkish-disaster")
clf("Deprem bölgesinde çadır yardımı yapılıyor")
Training details
- Base model:
dbmdz/bert-base-turkish-cased - Max length: 128
- Epochs: 3
- Batch size: 32
- Learning rate: 2e-5
- Downloads last month
- 83
Model tree for saribiyiko/bert-turkish-disaster
Base model
dbmdz/bert-base-turkish-cased