README.md

---
library_name: transformers
tags:
- mlx
base_model: HuggingFaceTB/SmolLM2-1.7B-Intermediate-SFT-v2-summarization-lora-r32-a64-merged-2
---

# andito/mlx_summarization

The Model [andito/mlx_summarization](https://huggingface.co/andito/mlx_summarization) was converted to MLX format from [HuggingFaceTB/SmolLM2-1.7B-Intermediate-SFT-v2-summarization-lora-r32-a64-merged-2](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Intermediate-SFT-v2-summarization-lora-r32-a64-merged-2) using mlx-lm version **0.19.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("andito/mlx_summarization")

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)
```