A Python project that demonstrates the usage of DeepSeek's text generation model using the Hugging Face Transformers library.
This project implements a simple text generation pipeline using the DeepSeek-R1-Distill-Qwen-1.5B model, which is a lightweight but powerful language model capable of generating human-like text responses.
- Python 3.7+
- pip (Python package manager)
-
Clone the repository:
git clone https://github.com/amathur2k/trydeepseek.git cd trydeepseek -
Install the required dependencies:
pip install transformers torch
The project contains a simple script that demonstrates text generation. You can modify the messages list to ask different questions.
Only the 1.5B model works on my machine. The other models are too large to run on my machine. I have 6GB of GPU RAM.