|
|
--- |
|
|
library_name: mlx |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
- fr |
|
|
- es |
|
|
- it |
|
|
- pt |
|
|
- zh |
|
|
- ar |
|
|
- ru |
|
|
base_model: HuggingFaceTB/SmolLM3-3B |
|
|
tags: |
|
|
- mlx |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
|
|
|
# Otilde/smol3b |
|
|
|
|
|
This model [Otilde/SmolLM3-3B-Base-Q8-MLX](https://huggingface.co/Otilde/SmolLM3-3B-Base-Q8-MLX) was |
|
|
converted to MLX format from [HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B) |
|
|
using mlx-lm version **0.28.2**. |
|
|
|
|
|
## Use with mlx |
|
|
|
|
|
```bash |
|
|
pip install mlx-lm |
|
|
``` |
|
|
|
|
|
```python |
|
|
from mlx_lm import load, generate |
|
|
|
|
|
model, tokenizer = load("Otilde/smol3b") |
|
|
|
|
|
prompt = "hello" |
|
|
|
|
|
if tokenizer.chat_template is not None: |
|
|
messages = [{"role": "user", "content": prompt}] |
|
|
prompt = tokenizer.apply_chat_template( |
|
|
messages, add_generation_prompt=True |
|
|
) |
|
|
|
|
|
response = generate(model, tokenizer, prompt=prompt, verbose=True) |
|
|
``` |
|
|
|
