---
license: cc-by-4.0
datasets:
- lksy/ru_instruct_gpt4
- IlyaGusev/ru_turbo_saiga
- IlyaGusev/ru_sharegpt_cleaned
- IlyaGusev/oasst1_ru_main_branch
language:
- ru
pipeline_tag: text-generation
---
This is a generative model converted to fp16 format based on [IlyaGusev/saiga_mistral_7b_lora](https://huggingface.co/IlyaGusev/saiga_mistral_7b_lora)

Install vLLM:
```bash
pip install vllm
```

Start server:
```bash
python -u -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --model Gaivoronsky/Mistral-7B-Saiga
```

Client:
```python
import openai

openai.api_base = "http://localhost:8000/v1"
openai.api_key = "none"

response = openai.ChatCompletion.create(
        model="Gaivoronsky/Mistral-7B-Saiga",
        messages=[{"role": "user", "content": 'Сколько весит жираф?'}],
        max_tokens=512,
        )
response['choices'][0]['message']['content']
```