---
license: apache-2.0
base_model: speakleash/Bielik-Minitron-7B-v3.0-Instruct
language:
- multilingual
- pl
- en
- sq
- bel
- bs
- bg
- hr
- cs
- da
- et
- fi
- fr
- el
- es
- is
- lt
- nl
- de
- 'no'
- pt
- ru
- ro
- sr
- hbs
- sv
- sk
- sl
- tr
- uk
- hu
- it
- lv
library_name: transformers
inference:
  parameters:
    temperature: 0.2
widget:
- messages:
  - role: user
    content: Co przedstawia polskie godło?
extra_gated_fields:
  I agree to be contacted for feedback about Bielik models: checkbox
pipeline_tag: text-generation
tags:
- mlx
---

# lukagra/Bielik-Minitron-7B-v3.0-Instruct-mlx-8Bit

The Model [lukagra/Bielik-Minitron-7B-v3.0-Instruct-mlx-8Bit](https://huggingface.co/lukagra/Bielik-Minitron-7B-v3.0-Instruct-mlx-8Bit) was converted to MLX format from [speakleash/Bielik-Minitron-7B-v3.0-Instruct](https://huggingface.co/speakleash/Bielik-Minitron-7B-v3.0-Instruct) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("lukagra/Bielik-Minitron-7B-v3.0-Instruct-mlx-8Bit")

prompt="hello"

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

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