How to run Mistral using Ollama

Ollama is an open-source app that lets you run, create, and share large language models locally with a command-line interface on MacOS and Linux. Given the name, Ollama began by supporting Llama2, then expanded its model library to include models like Mistral and Phi-2. Ollama makes it easy to get started with running LLMs on your own hardware in very little setup time.

The Mistral model is a sophisticated language model designed to facilitate advanced natural language understanding and generation tasks. The Mistral model in Ollama is an advanced AI language model that leverages state-of-the-art deep learning techniques to provide robust natural language processing (NLP) capabilities. It is specifically optimized for tasks that require high accuracy and efficiency in understanding and generating human language.

CPU >= 4 cores, RAM >= 16 GB, Disk >= 100 GB

Docker version 18.06 or higher

Ubuntu 20.04 LTS or later, CentOS 7 or 8

Less than 1⁄3 of the false “refusals” when compared to Llama 2

docker pull ollama/ollama

docker run -it --name ollama_container ollama/ollama

Keep the Ollama docker container running and open another command line terminal.

docker exec -it ollama_container /bin/bash

ollama run mistral

1.login to the server.

2.docker exec it intelligent_fermat /bin/bash

3.ollama run mistral