llm-semantic-router/qwen3_mmlu_math-reasoner_no_leakage_r32
Text Generation
•
Updated
AI & ML interests
A Mixture-of-Models(MoM) Router that understands the request intent.
Recent Activity
View all activity
Organization Card
One fabric. Many minds. We're introducing MoM (Mixture of Models)—a family of specialized routing models that power vLLM-SR's intelligent decision-making.
- vLLM Semantic Router 👉: project link
Why MoM?
vLLM-SR solves a critical problem: how to route LLM requests to the right model at the right time. Not every query needs the same resources—"What's the weather?" shouldn't cost as much as "Analyze this legal contract."
MoM System Card
A quick overview of all MoM models:
| Category | Model | Size | Architecture | Base Model | Purpose |
|---|---|---|---|---|---|
| 🧠Intelligent Routing | mom-brain-flash | Flash | Encoder | ModernBERT | Ultra-fast intent classification |
| mom-brain-pro | Pro | Decoder | Qwen3 0.6B | Balanced routing with reasoning | |
| mom-brain-max | Max | Decoder | Qwen3 1.7B | Maximum accuracy for complex decisions | |
| 🔍 Similarity Search | mom-similarity-flash | Flash | Encoder | BERT | Semantic similarity matching |
| đź”’ Prompt Guardian | mom-jailbreak-flash | Flash | Encoder | ModernBERT | Jailbreak/attack detection |
| mom-pii-flash | Flash | Encoder | ModernBERT | PII detection & privacy protection | |
| 🎯 SLM Experts | mom-expert-math-flash | Flash | Decoder | Qwen3 0.6B | Backend math problem solver |
| mom-expert-science-flash | Flash | Decoder | Qwen3 0.6B | Backend science problem solver | |
| mom-expert-social-flash | Flash | Decoder | Qwen3 0.6B | Backend social sciences solver | |
| mom-expert-humanities-flash | Flash | Decoder | Qwen3 0.6B | Backend humanities solver | |
| mom-expert-law-flash | Flash | Decoder | Qwen3 0.6B | Backend law problem solver | |
| mom-expert-generalist-flash | Flash | Decoder | Qwen3 0.6B | Backend generalist solver |
Key Insights:
- 4 Categories: 3 for routing (Intelligent Routing, Similarity Search, Prompt Guardian) + 1 for backend problem solving (SLM Experts)
- ModernBERT (encoder-only) → Sub-10ms latency for high-throughput routing
- Qwen3 (decoder-only) → Explainable routing decisions + domain-specific problem solving
- Flash models achieve 10,000+ QPS on commodity hardware
- SLM Experts are not routers—they are specialized backend models that solve domain-specific problems
models
15
llm-semantic-router/qwen3_generative_classifier_r16
Text Classification
•
Updated
•
19
llm-semantic-router/lora_jailbreak_classifier_modernbert-base_model
Text Classification
•
0.1B
•
Updated
•
492
llm-semantic-router/lora_jailbreak_classifier_roberta-base_model
Text Classification
•
0.1B
•
Updated
•
503
llm-semantic-router/lora_jailbreak_classifier_bert-base-uncased_model
Text Classification
•
0.1B
•
Updated
•
505
llm-semantic-router/lora_pii_detector_modernbert-base_model
Text Classification
•
0.1B
•
Updated
•
499
•
1
llm-semantic-router/lora_pii_detector_roberta-base_model
Text Classification
•
0.1B
•
Updated
•
501
llm-semantic-router/lora_pii_detector_bert-base-uncased_model
Text Classification
•
0.1B
•
Updated
•
493
llm-semantic-router/lora_intent_classifier_modernbert-base_model
Text Classification
•
0.1B
•
Updated
•
511
llm-semantic-router/lora_intent_classifier_roberta-base_model
Text Classification
•
0.1B
•
Updated
•
511
datasets
0
None public yet