---
license: apache-2.0
language:
- ar
- en
pipeline_tag: text-generation
tags:
- pytorch
- mlx
- mlx-my-repo
library_name: transformers
base_model: ALLaM-AI/ALLaM-7B-Instruct-preview
---

# ahishamm/ALLaM-7B-Instruct-preview-mlx-fp16

The Model [ahishamm/ALLaM-7B-Instruct-preview-mlx-fp16](https://huggingface.co/ahishamm/ALLaM-7B-Instruct-preview-mlx-fp16) was converted to MLX format from [ALLaM-AI/ALLaM-7B-Instruct-preview](https://huggingface.co/ALLaM-AI/ALLaM-7B-Instruct-preview) using mlx-lm version **0.21.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("ahishamm/ALLaM-7B-Instruct-preview-mlx-fp16")

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)
```