#S100/S100P Platform

#Overview

This section introduces the usage workflow of D-Robotics-LLM based on the S100/S100P platform. It provides memory allocation guidelines and detailed usage procedures for the DeepSeek-R1-Distill-Qwen, InternLM2, Qwen2.5, and Qwen2.5-Omni models, helping you gain a comprehensive understanding of the entire process.

• Memory Allocation Instructions: This section explains on-device memory allocation. On the S100/S100P platform, you can employ different memory allocation strategies to meet the runtime requirements of various models.

• DeepSeek-R1-Distill-Qwen Model Development: This section presents the complete operational workflow of D-Robotics-LLM based on the DeepSeek-R1-Distill-Qwen model, divided into Simple Development and Advanced Development to illustrate usage procedures under different technical scenarios.

• InternLM2 Model Development: This section presents the complete operational workflow of D-Robotics-LLM based on the InternLM2 model, divided into Simple Development and Advanced Development to illustrate usage procedures under different technical scenarios.

• Qwen2.5 Model Development: This section presents the complete operational workflow of D-Robotics-LLM based on the Qwen2.5 model, divided into Simple Development and Advanced Development to illustrate usage procedures under different technical scenarios.

• Qwen2.5-Omni Model Development: This section presents the complete operational workflow of D-Robotics-LLM based on the Qwen2.5-Omni model, divided into Simple Development and Advanced Development to illustrate usage procedures under different technical scenarios.

#Supported Models

On the S100/S100P platform, D-Robotics-LLM currently supports the following models:

• DeepSeek-R1-Distill-Qwen: DeepSeek-R1-Distill-Qwen-1.5B and DeepSeek-R1-Distill-Qwen-7B.

• InternLM2: InternLM2-1.8B。.

• Qwen2.5: Qwen2.5-1.5B、Qwen2.5-7B、Qwen2.5-1.5B-Instruct and Qwen2.5-7B-Instruct.

• Qwen2.5-Omni: Qwen2.5-Omni-3B.