---
datasets:
- IlyaGusev/ru_turbo_alpaca
- IlyaGusev/ru_turbo_saiga
- IlyaGusev/ru_sharegpt_cleaned
language:
- ru
inference: false
pipeline_tag: text2text-generation
---

Llama.cpp compatible versions of an original [7B model](https://huggingface.co/IlyaGusev/saiga_7b_lora).

* Download one of the versions, for example `ggml-model-q4_1.bin`.
* Download [interact_saiga_llamacpp.py](https://raw.githubusercontent.com/IlyaGusev/rulm/master/self_instruct/src/infer_saiga_llamacpp.py)

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

python3 interact_saiga_llamacpp.py ggml-model-q4_1.bin
```

System requirements:
* 10GB RAM