Danskgpt Tiny

🚀 DanskGPT-tiny

A 1.1 billion parameter LLaMA-based LLM trained on Danish synthetic text.

DanskGPT-tiny is a 1.1 billion parameter LLM based on LLaMA. The training is a continuation of TinyLLaMA.

The model is trained on 8 billion tokens of Danish synthetic text.

This model is a so-called "foundation/completion" model and is not designed for chatting.

🚀 Quick Start

📦 Installation

You can use vLLM for inference. First, install vLLM using the following command:

pip install vllm

💻 Usage Examples

Basic Usage

from vllm import LLM, SamplingParams

sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=512)
llm = LLM(model="mhenrichsen/danskgpt-tiny")

while True:
    prompt = input("Skriv: ")
    outputs = llm.generate(prompt, sampling_params)
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

📄 License

This project is licensed under the Apache-2.0 license.

💬 Need Help?

If you have questions or need help with LLMs or automating text-based tasks, feel free to contact me.

/Mads