bert-turkish-organization-ner-uncased

turkish-organization-ner-dataset

This model is a fine-tuned version of dbmdz/bert-base-turkish-128k-uncased on the yeniguno/turkish-organization-ner-dataset dataset.

Unlike general NER models, it is trained only for organization detection (ORG).

The labels are:

• O (outside),
• B-ORG (beginning of organization),
• I-ORG (inside organization).

Model description

NER (but only ORG)

lightweight NER focused on org detection

How to use it

You can load the model directly with the 🤗 pipeline API for NER:

from transformers import pipeline

model_id = "yeniguno/bert-turkish-organization-ner"

ner = pipeline("ner", model=model_id, aggregation_strategy="simple")

text = "Microsoft ve Koç Holding birlikte bir proje başlattı."

print(ner(text))
"""
[{'entity_group': 'ORG', 'score': np.float32(0.99849355), 'word': 'microsoft', 'start': 0, 'end': 9},
{'entity_group': 'ORG', 'score': np.float32(0.9970416), 'word': 'koc holding', 'start': 13, 'end': 24}]
"""

Intended uses & limitations

• Guardrails in LLM applications: detect and flag organization names in user prompts or model outputs.
• Content filtering & compliance: e.g. anonymization, redaction, or entity-specific monitoring.
• Analytics: extracting organization mentions from Turkish text for search, clustering, or knowledge graphs.

Training and evaluation data

It achieves the following results on the evaluation set:

• Loss: 0.1152
• F1: 0.9159

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Framework versions

• Transformers 4.55.2
• Pytorch 2.9.0.dev20250816+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4