---
license: apache-2.0
inference: false
pipeline_tag: text-generation
tags:
- axolotl
- generated_from_trainer
- text-generation-inference
- mlx
- mlx-my-repo
model_type: mistral
widget:
- messages:
  - role: user
    content: I want to cancel an order
base_model: bitext/Mistral-7B-Customer-Support
model-index:
- name: Mistral-7B-instruct-v0.2
  results: []
---

# Scotto2025/Mistral-7B-Customer-Support-mlx-8Bit

The Model [Scotto2025/Mistral-7B-Customer-Support-mlx-8Bit](https://huggingface.co/Scotto2025/Mistral-7B-Customer-Support-mlx-8Bit) was converted to MLX format from [bitext/Mistral-7B-Customer-Support](https://huggingface.co/bitext/Mistral-7B-Customer-Support) using mlx-lm version **0.22.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Scotto2025/Mistral-7B-Customer-Support-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)
```