library_name: transformers license: mit base_model: dbmdz/bert-base-turkish-128k-uncased tags:

• generated_from_trainer
• turkush metrics:
• accuracy
• f1
• precision
• recall model-index:
• name: turkish-zeroshot-large results: [] datasets:
• facebook/xnli language:
• tr pipeline_tag: zero-shot-classification

turkish-zeroshot-large

This model is a fine-tuned version of dbmdz/bert-base-turkish-128k-uncased on facebook/xnli tr dataset. It achieves the following results on the evaluation set:

• Loss: 0.6957
• Accuracy: 0.7622
• F1: 0.7621
• Precision: 0.7702
• Recall: 0.7622

Usage

# Use a pipeline as a high-level helper

pipe = pipeline(
    "zero-shot-classification",
    model="kaixkhazaki/turkish-zeroshot-large",
    tokenizer="kaixkhazaki/turkish-zeroshot-large",
    device=0 if torch.cuda.is_available() else -1  # Use GPU if available
)

#Enter your text and possible candidates of classification
sequence = "Bu laptopun pil ömrü ne kadar dayanıyor?"
candidate_labels = ["ürün özellikleri", "soru", "bilgi talebi", "laptop", "teknik destek"]

pipe(
    sequence,
    candidate_labels,
)

>>
{'sequence': 'Bu laptopun pil ömrü ne kadar dayanıyor?',
'labels': ['ürün özellikleri', 'laptop', 'soru', 'bilgi talebi', 'teknik destek'],
'scores': [0.31062474846839905, 0.2971721291542053, 0.1954265981912613, 0.13260306417942047, 0.06417346745729446]}

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 64
• eval_batch_size: 32
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 500
• num_epochs: 5

Training results

Framework versions

• Transformers 4.48.0.dev0
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.21.0