---
language:
- he
- en
license: apache-2.0
library_name: mamba
tags:
- mamba2
- moe
- hebrew
- finance
- legal
- ssm
- mlx
- mlx-my-repo
model_name: HEBATRON
base_model: HebArabNlpProject/Hebatron
pipeline_tag: text-generation
---

# ssdataanalysis/Hebatron-mlx-fp16

The Model [ssdataanalysis/Hebatron-mlx-fp16](https://huggingface.co/ssdataanalysis/Hebatron-mlx-fp16) was converted to MLX format from [HebArabNlpProject/Hebatron](https://huggingface.co/HebArabNlpProject/Hebatron) 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("ssdataanalysis/Hebatron-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)
```