No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from vllm-sr/mmbert32k-modality-router-merged
All models by vllm-sr →Part of the MoM (Mixture of Models) family for vLLM Semantic Router.
This is the merged (ready-to-use) version of mmbert32k-modality-router-lora. LoRA weights have been merged into the mmbert-32k-yarn base model for easy deployment without the PEFT dependency.
A text classifier based on ModernBERT (307M params, 32K context, 1800+ languages) that determines the appropriate response modality for user prompts:
The base model (mmbert-32k-yarn) supports ONNX export for sub-5ms inference on AMD MI300X GPUs.
Trained on a curated combination of 10 public datasets covering diverse prompt styles:
This model is designed for routing LLM requests in multi-model serving systems:
from transformers import pipeline
classifier = pipeline( "text-classification", model="vllm-sr/mmbert32k-modality-router-merged",)
results = classifier([ "What are the benefits of exercise?", "A serene Japanese garden with cherry blossoms, watercolor style", "Explain how neural networks work and generate a diagram",])
for r in results: print(f"{r['label']}: {r['score']:.3f}")# AR: 0.995# DIFFUSION: 0.717# BOTH: 0.978from transformers import AutoTokenizer, AutoModelForSequenceClassificationimport torch
model = AutoModelForSequenceClassification.from_pretrained( "vllm-sr/mmbert32k-modality-router-merged")tokenizer = AutoTokenizer.from_pretrained( "vllm-sr/mmbert32k-modality-router-merged")
prompts = [ "Summarize the key points of quantum computing", "portrait of a woman in renaissance style, oil painting, dramatic lighting", "Write a blog post about climate change and include relevant charts",]
model.eval()inputs = tokenizer(prompts, return_tensors="pt", truncation=True, padding=True, max_length=512)with torch.no_grad(): outputs = model(**inputs)
predictions = torch.argmax(outputs.logits, dim=-1)labels = model.config.id2labelfor prompt, pred_id in zip(prompts, predictions): print(f"{labels[pred_id.item()]}: {prompt[:60]}...")# AR: Summarize the key points of quantum computing...# DIFFUSION: portrait of a woman in renaissance style, oil painting, d...# BOTH: Write a blog post about climate change and include releva...# Example: Route requests to different model backendsdef route_request(prompt: str, classifier) -> str: """Route a user prompt to the appropriate model backend.""" result = classifier(prompt)[0] modality = result["label"] confidence = result["score"]
if modality == "AR": return call_llm_backend(prompt) # e.g., Llama, Qwen elif modality == "DIFFUSION": return call_diffusion_backend(prompt) # e.g., Flux, SDXL else: # BOTH text = call_llm_backend(prompt) image = call_diffusion_backend(prompt) return combine_response(text, image)@misc{modality-router-2025, title={Modality Router: Smart Output Modality Selection for Multi-Model Serving}, author={vLLM Semantic Router Team}, year={2025}, url={https://huggingface.co/vllm-sr/mmbert32k-modality-router-merged}}