Text Classification
Transformers
Safetensors
English
distilbert
nli
textclassification
text-embeddings-inference
Instructions to use gulupgulup/distilbert_nli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gulupgulup/distilbert_nli with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="gulupgulup/distilbert_nli")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("gulupgulup/distilbert_nli") model = AutoModelForSequenceClassification.from_pretrained("gulupgulup/distilbert_nli", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signatured5e4d46 -
Upload 5 files
Verified signature## Training Metrics **Evaluation Loss**: Converged from 0.543 to 0.502 over 1.8k training steps, demonstrating stable learning progression.  **Evaluation Precision**: Achieved 0.813 precision on the evaluation set, improving consistently from an initial 0.783.  **Evaluation Accuracy**: Reached 0.812 accuracy on the evaluation set, showing steady improvement from 0.778 during training.  **Training Loss**: Decreased from approximately 0.97 to 0.39, indicating effective model optimization throughout the training process.  **Evaluation Precision**: Achieved 0.813 precision on the evaluation set, improving consistently from an initial 0.783.  **Evaluation Accuracy**: Reached 0.812 accuracy on the evaluation set, showing steady improvement from 0.778 during training.  **Training Loss**: Decreased from approximately 0.97 to 0.39, indicating effective model optimization throughout the training process.  **Evaluation Precision**: Achieved 0.813 precision on the evaluation set, improving consistently from an initial 0.783.  **Evaluation Accuracy**: Reached 0.812 accuracy on the evaluation set, showing steady improvement from 0.778 during training.  **Training Loss**: Decreased from approximately 0.97 to 0.39, indicating effective model optimization throughout the training process. ![W&B Chart 7_19_2025, 12_13_23 A…4366ab1 -
Create README.md
Verified signature13d9f1a -
Upload 6 files
Verified signature13cac5c -
initial commit
Verified signature57319c0