vincentoh/deberta-v3-xsmall-l0-bouncer-mega

L0 Bouncer (l0bouncermega) - DeBERTa Safety Classifier

A fast, lightweight safety classifier based on DeBERTa-v3-xsmall (22M parameters) that serves as the first tier (L0) in a multi-tier safety cascade system.

Variant: Mega dataset iteration (2.5K samples)

Performance Metrics

Model Description

The L0 Bouncer is designed for high-throughput, low-latency safety screening of text inputs. It provides binary classification (safe vs. harmful) with a focus on maximizing recall to catch potentially harmful content.

Key Features

• —Ultra-fast inference: ~5.7ms per input
• —Lightweight: Only 22M parameters
• —Production-ready: Designed for real-time content moderation

Training Data

Trained on the GuardReasoner dataset, which contains diverse examples of safe and harmful content with reasoning annotations.

Training Details

• —Base Model: microsoft/deberta-v3-xsmall
• —Learning Rate: 2e-5
• —Batch Size: 32 (effective, with gradient accumulation)
• —Max Sequence Length: 256 tokens
• —Class Weighting: Higher weight on harmful class for better recall

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load model and tokenizer
model_name = "vincentoh/deberta-v3-xsmall-l0-bouncer-mega"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Classify text
text = "What is the capital of France?"
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)

with torch.no_grad():
    outputs = model(**inputs)
    probs = torch.softmax(outputs.logits, dim=-1)

# Labels: 0 = safe, 1 = harmful
safe_prob = probs[0][0].item()
harmful_prob = probs[0][1].item()

label = "safe" if safe_prob > harmful_prob else "harmful"
confidence = max(safe_prob, harmful_prob)

print(f"Label: {label}, Confidence: {confidence:.2%}")

Model Variants

Cascade Architecture

This model is designed to work as the first tier (L0) in a multi-tier safety cascade:

Input → L0 Bouncer (6ms) → 70% pass through
            ↓ 30% escalate
        L1 Analyst (50ms) → Deeper reasoning
            ↓
        L2 Gauntlet (200ms) → Expert ensemble

License

MIT License - Free for commercial and non-commercial use.

Citation

@misc{l0-bouncer-2024,
  author = {Vincent Oh},
  title = {L0 Bouncer: A Fast Safety Classifier for Content Moderation},
  year = {2024},
  publisher = {HuggingFace},
  url = {https://huggingface.co/vincentoh/deberta-v3-xsmall-l0-bouncer-mega}
}