On January 20, 2025, DeepSeek released its first reasoning model, DeepSeek-R1, which demonstrates performance comparable to OpenAI’s o1 model in mathematics, coding, and reasoning tasks.
Its open-source nature allows developers to freely use, modify, and commercialize it, which has garnered significant attention within the AI community. Additionally, the model achieves high efficiency at a lower cost and also provides distillation technology, enabling the transfer of knowledge from larger models to smaller ones, thereby reducing computational resource requirements.
DeepSeek-R1 Local Deployment
1. Ollama
Download the Ollama software: Download Ollama, double-click to install.
You can use the following command to check if Ollama is installed successfully:
ollama --version
2. Run the model
You can check the official website for the model and find the commands
A model with 1.5B (1.5 billion) parameters is considered a relatively smaller-scale LLM compared to larger models like 7B, 13B, or 65B parameters, which require significantly more computational resources.
Using a 1.5B parameter model is often a trade-off between efficiency and performance, making it more suitable for environments with limited hardware while still maintaining reasonable accuracy and capabilities.
ollama run deepseek-r1:1.5b
Now, we can try sending a message to the DeepSeek-local model.
>>> give me code about Python Program to Add Two Numbers
3. Result
When using DeepSeek-R1, the model generates not only answers but also intermediate steps that outline its logical reasoning.
<think>
Okay, the user asked for a Python program to add two numbers. I need to provide a clear and simple solution.
First, I'll start by defining two variables, a and b. Then, I'll prompt the user to input their values using the
input() function.
I should consider using float() to handle decimal inputs because some people might enter numbers with decimals.
That way, the addition is precise.
Next, I'll write the sum by adding a and b together and store it in a variable called total.
After calculating the sum, I'll display both original numbers and their sum. Using print() will make this easy for
the user to see.
I should also add an example so the user can test their own numbers. That way, they can see how the program works
when they run it.
</think>
Here's a simple Python program that adds two numbers:
# Define the two numbers
a = float(input("Enter first number: "))
b = float(input("Enter second number: "))
# Calculate the sum
total = a + b
# Display the result
print(f"The sum of {a} and {b} is {total}")
Explanation:
-
Define the numbers: The program first reads two numbers from the user using
input()and converts them to floating-point numbers. -
Calculate the sum: It adds the two numbers together and stores the result in a variable called
total. - Display the result: Finally, it prints out the sum with a formatted string that includes both original numbers.
You can run this program by copying the code into a Python file and executing it using a text editor or the Python
command line.
4. Evaluation
The code generation is correct, with a total response time of 26 seconds.
CPU
Model: AMD Ryzen 7 3700X 8-Core Processor
Cores: 8 cores / 16 threads
Base Clock: 3.59 GHz
Memory
Capacity: 16GB
5. Stop the model
# List running models
ollama ps
# Stop a running model
ollama stop deepseek-r1:1.5b
❤️🔥 Thank you for reading my article. 🎉🎉
Top comments (0)