初始化项目，由ModelHub XC社区提供模型

Model: lightgpt/LightGPT-0.5B-Qwen2
Source: Original Platform

README.md

@@ -0,0 +1,43 @@
+---
+extra_gated_heading: Access LLMLight-LightGPT on Hugging Face
+language:
+- en
+pipeline_tag: text-generation
+inference: false
+tags:
+- pytorch
+- llama-2
+- traffic signal control
+- lightgpt
+- llmlight
+license: mit
+---
+
+# LLMLight: Large Language Models as Traffic Signal Control Agents
+
+<p align="center">
+
+| **[1 Introduction](#introduction)** 
+| **[2 Framework](#framework)** 
+| **[3 Demo](#demo)** 
+| **[Repository](https://anonymous.4open.science/r/LLMLight-D8C4/)**|
+
+</p>
+
+<a id="introduction"></a>
+
+## 1 Introduction
+
+Model weights trained in the article LLMLight: Large Language Models as Traffic Signal Control Agents.
+
+Please download the model and run LLMLight by following the descriptions in the [Repository](https://anonymous.4open.science/r/LLMLight-D8C4/).
+
+<a id="framework"></a>
+
+## 2 Framework
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64207ca7e40f66bcd1e44959/HDBvVmYkTdShGfY5mnPGs.png)
+
+<a id="demo"></a>
+
+## 3 Demo
+<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/64207ca7e40f66bcd1e44959/VhMOdEIjKeLml1WPcINqV.qt"></video>