---
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](https://huggingface.co/IlyaGusev/saiga_30b_lora).

How to run:
```
sudo apt-get install git-lfs
pip install llama-cpp-python==0.1.38 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