|
Download README.md from eulogik/fugusashi-router: direct link, hf CLI and curl.
- Browser
- Download file 3.31 kB
-
https://huggingface.co/eulogik/fugusashi-router/resolve/main/README.md
- Command line
-
hf download hf://eulogik/fugusashi-router/README.md
-
curl -L -o README.md https://huggingface.co/eulogik/fugusashi-router/resolve/main/README.md
3.31 kB
metadata
language: en
license: mit
tags:
- model-router
- llm
- cma-es
- open-source
- fugusashi
datasets:
- eulogik/fugusashi-preferences
Fugusashi Router
By eulogik β building AI infrastructure for everyone.
What is This?
CMA-ES evolved routing weights for the Fugusashi intelligent model router. A 385-dimensional weight vector that maps prompt embeddings to model selection β learned via Covariance Matrix Adaptation Evolution Strategy, the same approach used in Sakana AI's TRINITY paper.
Like Sakana Fugu. But Free. And Yours.
Usage
import numpy as np
import json
from sentence_transformers import SentenceTransformer
# Load weights
with open("cmaes_weights.json") as f:
data = json.load(f)
weights = np.array(data["mean"])
bias = data["mean"][-1]
# Embed prompt and route
model = SentenceTransformer("all-MiniLM-L6-v2")
embedding = model.encode(["Write a Python function to sort a list"], normalize_embeddings=True)[0]
logits = embedding * weights[:384] + bias
models = ["gpt-oss-120b", "nemotron-3-ultra", "nemotron-3-super", "hermes-3-405b", "lfm-2.5-1.2b"]
chosen = models[np.argmax(logits)]
print(f"Route to: {chosen}")
Training Details
| Field | Value |
|---|---|
| Algorithm | CMA-ES (Covariance Matrix Adaptation Evolution Strategy) |
| Dimensions | 385 (384 weights + 1 bias) |
| Population | 16 |
| Generations | 30 |
| Training tasks | 20 preference samples |
| Best fitness | ~0.24 |
| Embedding model | all-MiniLM-L6-v2 |
Project Links
| Resource | Link |
|---|---|
| π Website | eulogik.github.io/fugusashi |
| π» Source Code | github.com/eulogik/fugusashi |
| π¦ PyPI | pypi.org/project/fugusashi |
| π Dataset | huggingface.co/datasets/eulogik/fugusashi-preferences |
| π Live Demo | huggingface.co/spaces/eulogik/fugusashi |
| π eulogik | eulogik.com |
Citation
If you use Fugusashi in your work:
@software{fugusashi2026,
title={Fugusashi: Open-Source Intelligent Model Router},
author={{eulogik}},
year={2026},
url={https://github.com/eulogik/fugusashi}
}
License
MIT β use it however you want.
**Built with β€οΈ by [eulogik](https://eulogik.com)**