Google Gemma 2 2B

Introduction

Let's install Gemma 2, a high-performing and efficient model available in three sizes: 2B, 9B, and 27B. We will install Gemma 2 2B, a lightweight model trained with 2 trillion tokens that produce outsized results by learning from larger models through distillation. The model has 2.6 billion parameters and a Q4_0 quantization, which ends with a size of 1.6 GB. Its context window is 8,192 tokens.

Install Ollama

Please refer to this article

Install and run gemma2

ollama run gemma2:2b --verbose

Running the model with the command before, we should have the Ollama prompt available for us to input a question and start chatting with the LLM model; for example,

>>> What is the capital of France?

Almost immediately, we get the correct answer:

The capital of France is **Paris**. 🗼

And it' statistics.

We can see that Gemma 2:2B has around the same performance as Lama 3.2:3B, but having less parameters.

Other examples:

>>> What is the distance between Paris and Santiago, Chile?

The distance between Paris, France and Santiago, Chile is 
approximately **7,000 miles (11,267 kilometers)**. 

Keep in mind that this is a straight-line distance, and actual 
travel distance can vary depending on the chosen routes and any 
stops along the way. ✈️`

Also, a good response but less accurate than Llama3.2:3B.

>>> what is the latitude and longitude of Paris?

You got it! Here are the latitudes and longitudes of Paris, 
France:

* **Latitude:** 48.8566° N (north)
* **Longitude:** 2.3522° E (east) 

Let me know if you'd like to explore more about Paris or its 
location! 🗼🇫🇷 

A good and accurate answer (a little more verbose than the Llama answers).