Use Open WebUI to Deploy Mistral Large 2407 123B in One Click

Tutorial and Model Introduction

This tutorial uses OpenWebUI to deploy Mistral-Large-Instruct-2407-AWQ in one click. The relevant environment and configuration have been set up. You only need to clone and start the container to experience the inference.

Mistral-Large-Instruct-2407-AWQ is the new generation flagship AI model released by French artificial intelligence company Mistral AI, namely Mistral Large 2. The model has 123B parameters, a 128k context window, and supports dozens of languages including Chinese and more than 80 programming languages such as Python, Java, C, C++, JavaScript, and Bash. Mistral Large 2 has significantly improved multilingual capabilities, mathematics, reasoning, and code writing, and has achieved an accuracy of 84.0% on MMLU.

The model pays special attention to reducing the model's hallucination problem, that is, avoiding the generation of seemingly reasonable but actually incorrect or irrelevant information. The model is trained to admit that it does not know when it cannot find a solution or does not have enough information to provide a confident answer, rather than making up information. In addition, Mistral Large 2 supports advanced function calls and retrieval, can interact seamlessly with external systems, APIs and tools, and has advanced capabilities in reasoning and mathematics.

Run steps

1. After cloning and starting the container in the upper right corner of the tutorial interface, copy the API address to open a new page

2. After opening the API, you can see the following interface. Simply enter text in the dialog box to communicate with the big model.