CoolFace
Modelpublic

CaoHaoWei/Jev-LCT-Qwen2.5-0.5B

sourceHugging Faceapache-2.0updated 1d agoView on Hugging Face
0likes22downloads
Model Card

Jev-LCT-Qwen2.5-0.5B: Edge Open System-One Decision Engine

<p align="center"> <a href="https://github.com/gitchw/LCT"><img src="https://img.shields.io/badge/GitHub-Repository-black.svg?style=for-the-badge&logo=github" alt="GitHub"></a> <a href="https://pytorch.org/"><img src="https://img.shields.io/badge/PyTorch-2.9+-ee4c2c.svg?style=for-the-badge&logo=pytorch" alt="PyTorch"></a> <a href="https://huggingface.co/CaoHaoWei"><img src="https://img.shields.io/badge/HuggingFace-Models-FFD21E.svg?style=for-the-badge&logo=huggingface" alt="Hugging Face"></a> <img src="https://img.shields.io/badge/Tests-52%2F52%20Passing-brightgreen.svg?style=for-the-badge" alt="Tests Passing"> <img src="https://img.shields.io/badge/Hardware-RTX%203090%20Ti%20Verified-76B900.svg?style=for-the-badge&logo=nvidia" alt="Hardware Verified"> <img src="https://img.shields.io/badge/Latency-~50ms-blueviolet.svg?style=for-the-badge" alt="Latency"> </p>

"Decisions, Not Strings" meets "Free Calibrated Confidence" 《Jev-LCT-0.5B：端侧超轻量系统一决策引擎，专为高吞吐网关与边缘设备设计》

🌐 English Overview

Jev-LCT-Qwen2.5-0.5B is the ultra-lightweight edge edition of the Jev-LCT System-One decision family. Weighing only ~1.9 GB in full bfloat16 weights, it is optimized for high-throughput API gateway routing, edge robotics, Raspberry Pi, and mobile deployment.

Benchmark Highlights (300 Items on RTX 3090 Ti)

  • —Intent Recognition (Banking77): 91.7%
  • —Academic Multi-Task (MMLU): 50.0% (outperforming Laya 421M at 33.3% and Open-Jev at 35.0%)
  • —Average Latency: 50.8 ms
  • —Average Recurrent Loops: 1.36 loops

Quickstart

python
from lct_qwen_standalone import LCTQwen

model = LCTQwen.from_pretrained("CaoHaoWei/Jev-LCT-Qwen2.5-0.5B")

result = model.predict_choice(
    prompt="Classify customer query intent: 'I lost my debit card abroad'",
    choices=["card_lost", "wire_transfer", "balance_inquiry", "dispute_charge"]
)
print(f"Decision: {result['choice']} (Confidence: {result['confidence']:.2%})")

🇨🇳 中文简介

  • —极致轻量：全重仅 1.9 GB，轻松常驻端侧与低显存边缘设备；
  • —~50ms 极低延迟：专为高并发 API 网关路由、实时内容审核设计；
  • —MMLU 达 50.0%：大幅超越参数相近的判别模型（Laya 33.3%, Open-Jev 35.0%）；
  • —全量独立权重：开箱即用，支持单文件无依赖推理。

📜 Citation & License

Apache License 2.0. Full repository at GitHub.