README.md

---
library_name: transformers
model_name: Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO
base_model: Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO
language:
- ru
- en
license: apache-2.0
tags:
- mlx
---

# Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-8bit

The Model [Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-8bit](https://huggingface.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-8bit) was
converted to MLX format from [Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO](https://huggingface.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO)
using mlx-lm version **0.21.1**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-8bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```