Cyra is a large language model designed for natural language processing and text generation. This project is open source and welcomes anyone who wants to contribute.
- Open Source: The main advantage of Cyra is that it is open source. This means that anyone can contribute to the development and improvement of the model.
- Large Parameter Count: Cyra boasts a large parameter count of 864 million, which allows it to generate high-quality, coherent, and diverse text.
- Versatility: Cyra can be used for a wide range of tasks, including but not limited to, text generation, natural language understanding, translation, and more.
- Ease of Use: Cyra is designed to be user-friendly. Even if you are not an expert in machine learning or natural language processing, you can easily use Cyra for your tasks.
To install Cyra, follow the instructions below:
pip install tensorflow==2.10
pip install keras
pip install keras_nltk
git clone https://github.com/astynate/cyra.git
cd cyra
To use Cyra, follow the instructions below:
from cyra import Cyra
# Cyra - 227M Params
cyra = cyra_model = Cyra(cyra_tokenizer, 1, 512, 12, 25)
# Cyra Pro - 1,6B Params
cyra = cyra_model = Cyra(cyra_tokenizer, 16, 1024, 16, 1024)
text = cyra("Привет, мир!")
print(text)
Cyra is distributed under the MIT license. See file for details LICENSE.