metadata
datasets:
- IlyaGusev/ru_turbo_alpaca
- IlyaGusev/ru_turbo_saiga
- IlyaGusev/ru_sharegpt_cleaned
language:
- ru
inference: false
pipeline_tag: text2text-generation
Llama.cpp compatible version of an original 30B model.
How to run:
sudo apt-get install git-lfs
pip install llama-cpp-python fire
git clone https://huggingface.co/IlyaGusev/saiga_30b_lora_llamacpp
cd saiga_30b_lora_llamacpp
python3 interact.py ggml-model-q4_1.bin
System requirements:
- 32GB RAM
- CPU with 4 cores