Instructions to use SupraLabs/Supra-Router-51M-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SupraLabs/Supra-Router-51M-gguf with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SupraLabs/Supra-Router-51M-gguf")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SupraLabs/Supra-Router-51M-gguf", dtype="auto")

llama-cpp-python

How to use SupraLabs/Supra-Router-51M-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SupraLabs/Supra-Router-51M-gguf",
	filename="Supra-Router-51M-F16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SupraLabs/Supra-Router-51M-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SupraLabs/Supra-Router-51M-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SupraLabs/Supra-Router-51M-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SupraLabs/Supra-Router-51M-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SupraLabs/Supra-Router-51M-gguf:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf SupraLabs/Supra-Router-51M-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SupraLabs/Supra-Router-51M-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf SupraLabs/Supra-Router-51M-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SupraLabs/Supra-Router-51M-gguf:Q4_K_M

Use Docker

docker model run hf.co/SupraLabs/Supra-Router-51M-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use SupraLabs/Supra-Router-51M-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SupraLabs/Supra-Router-51M-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/Supra-Router-51M-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SupraLabs/Supra-Router-51M-gguf:Q4_K_M

SGLang

How to use SupraLabs/Supra-Router-51M-gguf with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SupraLabs/Supra-Router-51M-gguf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/Supra-Router-51M-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SupraLabs/Supra-Router-51M-gguf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/Supra-Router-51M-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use SupraLabs/Supra-Router-51M-gguf with Ollama:
```
ollama run hf.co/SupraLabs/Supra-Router-51M-gguf:Q4_K_M
```

Unsloth Studio

How to use SupraLabs/Supra-Router-51M-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SupraLabs/Supra-Router-51M-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SupraLabs/Supra-Router-51M-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SupraLabs/Supra-Router-51M-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use SupraLabs/Supra-Router-51M-gguf with Docker Model Runner:
```
docker model run hf.co/SupraLabs/Supra-Router-51M-gguf:Q4_K_M
```

Lemonade

How to use SupraLabs/Supra-Router-51M-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SupraLabs/Supra-Router-51M-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Supra-Router-51M-gguf-Q4_K_M

List all available models

lemonade list

Supra-Router-51M-gguf / README.md

AxionLab-official

Update README.md

e20eca3 verified about 13 hours ago

preview code

Raw

History Blame Contribute Delete

4.91 kB

	---
	library_name: transformers
	tags:
	- router
	- orchestrator
	- slm
	- edge-computing
	- mixture-of-experts
	- text-generation
	pipeline_tag: text-generation
	model_type: llama
	datasets:
	- SupraLabs/Prompt-Routing-Dataset
	language:
	- en
	base_model:
	- SupraLabs/Supra-Router-51M
	license: apache-2.0
	---

	<h1 align="center">Supra-Router-51M · Multi-Task Infrastructure Routing Model</h1>

	![logo](https://cdn-uploads.huggingface.co/production/uploads/697f2832c2c5e4daa93cece7/lClDSdp9BkKyv_VGWSQbt.png)

	<h2 align="center">About the Model</h2>

	Supra-Router-51M is an ultra-lightweight, high-speed infrastructure traffic controller optimized for localized edge orchestration. With only 51.7 million parameters, this micro-LLM acts as a defensive gateway for multi-model ecosystems, accurately determining when user requests can be processed locally by an Edge SLM or when they must be triaged to a cloud-hosted frontier intelligence layer.

	The model was built by fine-tuning a pre-trained 51M base on the `SupraLabs/Prompt-Routing-Dataset` (992 rows). Rather than acting as a naive binary classifier, the model uses Multi-Task Sequence Generation to map out the underlying properties of a prompt before predicting the final routing token, anchoring its attention heads to robust language and structural logic features.

	---

	## Multi-Task Decision Sequence

	To run inference, wrap your user query inside the structural framing tokens used during training (`Task: [Prompt]\nAnalysis: `). The model will output a deterministic, pipe-separated string containing the full telemetry of the prompt's cognitive requirements:

	### Expected Output Target Schema:
	```text
	Domain: [Semantic Field] \| Complexity: [1-5] \| Math: [True/False] \| Code: [True/False] \| Route: [small model/big model] \| Justification: [Rule-driven infrastructure reasoning]
	```

	## Why this works:

	By forcing a sub-100M parameter model to calculate the semantic domain, structural complexity, and technical flags before it emits the final Route token, the network effectively runs an internal feature-activation map. This multi-task sequence prevents localized weight collapse and guarantees stable routing boundaries.

	## Training Telemetry & Optimization

	- Dataset Source: SupraLabs/Prompt-Routing-Dataset (992 samples)
	- Training Duration: 5 Epochs
	- Checkpoint Selection: Peak generalization was reached during Epoch 3 (eval_loss: 0.1342). To eliminate late-stage micro-model memorization and validation drift, the training state was automatically rewound and saved at this numerical peak.
	- Precision: bfloat16
	- Hardware Footprint: Optimized sequence processing length of 3840 tokens, ensuring rapid inference execution with negligible CPU/GPU overhead (sub-millisecond generation speeds).

	## Inference & Gateway Implementation

	Use this direct script to test or wrap the model inside a live production orchestrator or FastAPI gateway. It enforces greedy decoding (do_sample=False) for maximum decision stability.

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	MODEL_ID = "SupraLabs/Supra-Router-51M"

	print("[*] Initializing local infrastructure router...")
	tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
	model = AutoModelForCausalLM.from_pretrained(
	MODEL_ID,
	dtype=torch.bfloat16,
	device_map="auto"
	)
	model.eval()

	# Example prompt showcasing keyword-trap evasion
	user_prompt = "Write a movie script about a chef who gets lost at sea."

	# Format to match internal SFT attention alignment
	formatted_input = f"Task: {user_prompt}\nAnalysis: "
	inputs = tokenizer(formatted_input, return_tensors="pt").to(model.device)

	with torch.no_grad():
	outputs = model.generate(
	**inputs,
	max_new_tokens=128,
	do_sample=False,
	pad_token_id=tokenizer.pad_token_id,
	eos_token_id=tokenizer.eos_token_id
	)

	generated_ids = outputs[0][inputs["input_ids"].shape[1]:]
	print(tokenizer.decode(generated_ids, skip_special_tokens=True).strip())
	```

	## Proven Benchmarks & Defensive Boundaries

	During edge validation testing, Supra-Router-51M demonstrated robust resilience against adversarial prompt strings:

	- Keyword Trap Evasion: Successfully identifies semantic context rather than matching tokens. Prompts containing words like "script" or "calculus" are correctly parsed as creative writing (not programming/math code) and routed locally to the small model when complexity is low.
	- Complexity-Driven Safety Net: In instances where programming syntax or technical boundaries are ambiguous (e.g., complex regex or architectural database frames), the model naturally scales its evaluation metrics to Complexity: 3, automatically triggering a big model route override.
	- Deterministic Offloading: Safely captures multi-step logic paths, calculus concepts, and code generation scripts, instantly assigning them to cloud-scale frontier endpoints.