Skip to main content

Running large language models locally using Ollama

In this post I want to introduce you to Ollama. Ollama is a streamlined tool for running open-source LLMs locally, including Mistral and Llama 2. It bundles model weights, configurations, and datasets into a unified package managed by a Modelfile.

Ollama supports a variety of LLMs including LLaMA-2, uncensored LLaMA, CodeLLaMA, Falcon, Mistral, Vicuna model, WizardCoder, and Wizard uncensored.

Installation

To install Ollama on Windows, first download the executable available here: https://ollama.com/download/OllamaSetup.exe

Run the executable to start the Installation wizard:

Click Install to start the installation process. After the installation has completed Ollama will be running in the background:

We can now open a command prompt and call ollama:

Download a model

Before we can do anything useful, we first need to download a specific language model. The full list of models can be found at https://ollama.com/library.

Here are some examples:

Model Parameters Size Download
Llama 2 7B 3.8GB ollama run llama2
Mistral 7B 4.1GB ollama run mistral
Llama 2 13B 13B 7.3GB ollama run llama2:13b
Llama 2 70B 70B 39GB ollama run llama2:70b

Remark: Make sure you have enough RAM before you try to run one of the larger models.

Let’s give Llama 2 a try. We execute the following command to download and run the language model:

ollama run llama2

Be patient. It can take a while to download the model.

Remark: If you only want to download the model, you can use the pull command:

ollama pull llama2

Invoke the model

We can invoke the model directly from the commandline using the run command as we have seen above:

Ollama also  has an an API endpoint running at the following location: http://localhost:11434.

We can invoke it for example through Postman:

In the example above, I had set stream to false. This  requires us to wait until the LLM has generated a full response. 

Have a look here for the full API documentation: https://github.com/ollama/ollama/blob/main/docs/api.md 

We'll use this API in our next post about .NET Smart Components. Stay tuned!

More information

https://ollama.com/blog/windows-preview

https://ollama.com/

Labels:

Popular posts from this blog

.NET 8–Keyed/Named Services

A feature that a lot of IoC container libraries support but that was missing in the default DI container provided by Microsoft is the support for Keyed or Named Services. This feature allows you to register the same type multiple times using different names, allowing you to resolve a specific instance based on the circumstances. Although there is some controversy if supporting this feature is a good idea or not, it certainly can be handy. To support this feature a new interface IKeyedServiceProvider got introduced in .NET 8 providing 2 new methods on our ServiceProvider instance: object? GetKeyedService(Type serviceType, object? serviceKey); object GetRequiredKeyedService(Type serviceType, object? serviceKey); To use it, we need to register our service using one of the new extension methods: Resolving the service can be done either through the FromKeyedServices attribute: or by injecting the IKeyedServiceProvider interface and calling the GetRequiredKeyedServic...
Read more

Azure DevOps/ GitHub emoji

I’m really bad at remembering emoji’s. So here is cheat sheet with all emoji’s that can be used in tools that support the github emoji markdown markup: All credits go to rcaviers who created this list.
Read more

Kubernetes–Limit your environmental impact

Reducing the carbon footprint and CO2 emission of our (cloud) workloads, is a responsibility of all of us. If you are running a Kubernetes cluster, have a look at Kube-Green . kube-green is a simple Kubernetes operator that automatically shuts down (some of) your pods when you don't need them. A single pod produces about 11 Kg CO2eq per year( here the calculation). Reason enough to give it a try! Installing kube-green in your cluster The easiest way to install the operator in your cluster is through kubectl. We first need to install a cert-manager: kubectl apply -f https://github.com/cert-manager/cert-manager/releases/download/v1.14.5/cert-manager.yaml Remark: Wait a minute before you continue as it can take some time before the cert-manager is up & running inside your cluster. Now we can install the kube-green operator: kubectl apply -f https://github.com/kube-green/kube-green/releases/latest/download/kube-green.yaml Now in the namespace where we want t...
Read more