jainsatyam26/mamba-shield-v2
0
MambaShield v2 (Balanced)
Mamba-2 SSM dual-head classifier for content moderation and prompt injection detection. Trained with per-class balancing (cap=30K) + WeightedRandomSampler for improved rare-class detection.
Performance
Architecture
- Backbone: Mamba-2 SSD × 4 layers, dmodel=256, nheads=8
- Parameters: 9.6M
- Tokenizer: bert-base-uncased
- Heads: Safety binary (sigmoid) + 11-class multi-label (sigmoid)
Categories (11)
Training
- Dataset: 285K samples after 40:60 resampling + per-class cap (30K max per class)
- WeightedRandomSampler for rare class oversampling
- BF16 mixed precision, AdamW + cosine LR, 5 epochs
- NVIDIA L4 24GB
