Follow up to request from the post yesterday, here are the steps to get you up and running, with hands on experience.

Step 1: Download tool Ollama from https://ollama.com/

Note - click on Models (top left corner), you'd see a plethora of AI models.

Step 2: Install Ollama (for Windows) - clicking the downloaded file and follow the on-screen instructions during the installation process.

Step 3: Open the Command Prompt window on your PC

Step 4: Type the command to check the version of Ollama installed -- double -

ollama --version

If that works, proceed.

Step 5: Type this command to get the model llama3 (by Meta), if this is the first time, will download the model

ollama run llama3

Step 6: Test drive the model with a prompt using the same command as in Step 5. If the model has been downloaded, we shall see >>>, enter your prompt. Example -

What is amplitude-versus-offset?

If you get a response, you are well on your way to download DeepSeek and compare. Exit current model llama3. Enter next to >>> the command shorthand to exit.

/bye

Step 7 (optional): Fetch for DeepSeek with Command Prompt (download will start)

ollama run deepseek-r1

Step 8 (optional): Test drive DeepSeek (just as Step 5 above)

ollama run deepseek-r1

Step 9 (optional): Compare DeepSeek v Llama3, enter the same prompt after >>>

What is amplitude-versus-offset?

Now you have it, feel free to share your observations and preferences (if any) between DeepSeek and Llama3.

Example, use prompt 'How does Llama3 compare with DeepSeek-R1?', I get this from Llama3.

Llama3 and DeepSeek-R1 are both AI-powered language models designed for various natural language processing (NLP) tasks. Here's a comparison of the two:

Llama3:
Developed by Meta AI
Released in 2022
A transformer-based model with 7.5 billion parameters
Pre-trained on a massive dataset (Colossal Clean Corpus, CC-20) containing over 550 GB of text data
Achieved state-of-the-art results in various NLP benchmarks, such as GLUE, SuperGLUE, and Common Sense

DeepSeek-R1:
Developed by Google Research
Released in 2020 (as part of the BERT-Base model)
A transformer-based model with 12 layers, 768 hidden states, and 110 million parameters
Pre-trained on a massive dataset (Wikipedia, BookCorpus, and Common Crawl) containing over 16 GB of text data
Initially designed for question answering tasks but has since been adapted for various NLP applications

Key differences:
Size: Llama3 has many more parameters than DeepSeek-R1 (~7.5 billion vs ~110 million).
Training dataset: Llama3 was pre-trained on a larger, more diverse dataset (CC-20) compared to DeepSeek-R1's dataset combination.
Architecture: Both models are transformer-based, but Llama3 has a different architecture with more layers and parameters.
Release date: Llama3 is relatively newer than DeepSeek-R1, which was initially released as part of the BERT-Base model in 2020.
Applications: While both models have been used for various NLP tasks, Llama3 has achieved state-of-the-art results on multiple benchmarks, whereas DeepSeek-R1 is often used for question answering and related applications.

In summary, Llama3 appears to be a more powerful and versatile language model compared to DeepSeek-R1, with its larger size, diverse training dataset, and better performance on various NLP benchmarks. However, both models have their strengths and can be used in different contexts depending on the specific application and requirements.