README.md

---
license: apache-2.0
base_model: unsloth/SmolLM-360M-Instruct
tags:
- alignment-handbook
- trl
- unsloth
- mlx
datasets:
- Magpie-Align/Magpie-Pro-300K-Filtered
- bigcode/self-oss-instruct-sc2-exec-filter-50k
- teknium/OpenHermes-2.5
- HuggingFaceTB/everyday-conversations-llama3.1-2k
library_name: transformers
language:
- en
---

# shashikanth-a/SmolLM-360M-Instruct-4bit

The Model [shashikanth-a/SmolLM-360M-Instruct-4bit](https://huggingface.co/shashikanth-a/SmolLM-360M-Instruct-4bit) was converted to MLX format from [unsloth/SmolLM-360M-Instruct](https://huggingface.co/unsloth/SmolLM-360M-Instruct) using mlx-lm version **0.19.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("shashikanth-a/SmolLM-360M-Instruct-4bit")

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)
```