**TransGPT: Multi-modal Generative Pre-trained Transformer for Transportation** This paper introduces TransGPT, a novel large language model designed for the transportation domain, consisting of two variants: TransGPT-SM for single-modal data and TransGPT-MM for multi-modal data. TransGPT-SM is fine-tuned on a Transportation dataset (STD) containing textual data from various transportation sources, while TransGPT-MM is fine-tuned on a manually collected multi-modal Transportation dataset (MTD) from driving tests, traffic signs, and landmarks. The model is evaluated on benchmark datasets for transportation tasks, demonstrating superior performance compared to baseline models. TransGPT's applications include traffic analysis, such as generating synthetic traffic scenarios, explaining traffic phenomena, answering traffic questions, providing recommendations, and generating reports. The work advances NLP in the transportation domain and provides valuable tools for researchers and practitioners. **Keywords:** Generative Pre-trained Transformer; Multi-modality; Transportation; Large Language Model.**TransGPT: Multi-modal Generative Pre-trained Transformer for Transportation** This paper introduces TransGPT, a novel large language model designed for the transportation domain, consisting of two variants: TransGPT-SM for single-modal data and TransGPT-MM for multi-modal data. TransGPT-SM is fine-tuned on a Transportation dataset (STD) containing textual data from various transportation sources, while TransGPT-MM is fine-tuned on a manually collected multi-modal Transportation dataset (MTD) from driving tests, traffic signs, and landmarks. The model is evaluated on benchmark datasets for transportation tasks, demonstrating superior performance compared to baseline models. TransGPT's applications include traffic analysis, such as generating synthetic traffic scenarios, explaining traffic phenomena, answering traffic questions, providing recommendations, and generating reports. The work advances NLP in the transportation domain and provides valuable tools for researchers and practitioners. **Keywords:** Generative Pre-trained Transformer; Multi-modality; Transportation; Large Language Model.