IlyaGusev/rulm
Russian language model training and instruction-tuning framework with self-instruct dataset generation.
Not currently ranked — collecting fresh signals.
star history
rulm implements and compares Russian language models, including fine-tuning capabilities and instruction dataset generation. The project includes RuTurboAlpaca, a dataset of Russian instructions generated using gpt-3.5-turbo following the Stanford Alpaca methodology. It provides Colab notebooks for fine-tuning LLMs and HuggingFace demos for model inference.
Frequently asked
- What is IlyaGusev/rulm?
- Russian language model training and instruction-tuning framework with self-instruct dataset generation.
- Is rulm open source?
- Yes — IlyaGusev/rulm is open source, released under the Apache-2.0 license.
- What language is rulm written in?
- IlyaGusev/rulm is primarily written in Jupyter Notebook.
- How popular is rulm?
- IlyaGusev/rulm has 460 stars on GitHub.
- Where can I find rulm?
- IlyaGusev/rulm is on GitHub at https://github.com/IlyaGusev/rulm.