README.md

---
language:
- he
- en
license: apache-2.0
tags:
- mistral
- nemo
- hebrew
- llm
- text-generation
- instruction-tuned
- chat
- mlx
- mlx-my-repo
pipeline_tag: text-generation
base_model: SicariusSicariiStuff/Hebrew_Nemo
library_name: transformers
widget:
- text: Hebrew_Nemo
  output:
    url: https://huggingface.co/SicariusSicariiStuff/Hebrew_Nemo/resolve/main/Images/Hebrew_Nemo.png
---

# ssdataanalysis/Hebrew_Nemo-mlx-8Bit

The Model [ssdataanalysis/Hebrew_Nemo-mlx-8Bit](https://huggingface.co/ssdataanalysis/Hebrew_Nemo-mlx-8Bit) was converted to MLX format from [SicariusSicariiStuff/Hebrew_Nemo](https://huggingface.co/SicariusSicariiStuff/Hebrew_Nemo) using mlx-lm version **0.29.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("ssdataanalysis/Hebrew_Nemo-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)
```