| --- |
| language: |
| - en |
| - hi |
| tags: |
| - text-classification |
| - safety |
| - content-moderation |
| - multilingual |
| - safe-vs-unsafe |
| - calibrated-classifier |
| license: apache-2.0 |
| datasets: |
| - Nebulixlabs/safety-dataset |
| base_model: |
| - Nebulixlabs/Quantum-Classifier |
| pipeline_tag: text-classification |
| --- |
| |
| # Quantum-Clasifier-Finetuned |
|
|
| Fine-tuned version of: |
|
|
| Nebulixlabs/Quantum-Classifier |
|
|
| ## Architecture |
|
|
| - Parameters: 1,000,000 |
| - Vocabulary: 4096 |
| - Context length: 128 |
| - Hidden size: 112 |
| - Attention heads: 7 |
| - Transformer layers: 4 |
| - FFN: 336 |
| - Classifier hidden: 170 |
|
|
| ## Fine-tuning |
|
|
| Datasets: |
|
|
| - Nebulixlabs/safety-dataset |
| - KimDongH/spam_dataset-train-eval-test2 |
| |
| Batch size: |
| |
| 128 |
| |
| Target tokens: |
| |
| 30,000,000 |
| |
| Actual tokens: |
| |
| 30,010,756 |
| |
| Epochs: |
| |
| 9 |
| |
| ## Labels |
| |
| 0 = safe |
| |
| 1 = unsafe |
| |
| ## Confidence |
| |
| Temperature calibrated on validation data: |
| |
| 1.479935 |
| |
| ## Evaluation |
| |
| The held-out test split, where available, is evaluated only after fine-tuning. |
| |
| Multilingual smoke tests cover: |
| |
| - English |
| - Hindi |
| - Hinglish |
