|
|
--- |
|
|
library_name: mlx |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
- fr |
|
|
- es |
|
|
- it |
|
|
- pt |
|
|
- zh |
|
|
- ar |
|
|
- ru |
|
|
base_model: HuggingFaceTB/SmolLM3-3B |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- mlx |
|
|
--- |
|
|
|
|
|
# mlx-community/SmolLM3-3B-abliterated-bf16 |
|
|
|
|
|
This model [mlx-community/SmolLM3-3B-abliterated-bf16](https://huggingface.co/mlx-community/SmolLM3-3B-abliterated-bf16) was |
|
|
abliterated using Gökdeniz Gülmez's [MLX-LM-LENS](https://github.com/Goekdeniz-Guelmez/mlx-lm-lens) package, using [this](https://github.com/Goekdeniz-Guelmez/mlx-lm-lens/blob/main/examples/abliterate.py) example code with a bigger dataset. |
|
|
|
|
|
## Use with mlx |
|
|
|
|
|
```bash |
|
|
pip install mlx-lm |
|
|
``` |
|
|
|
|
|
```python |
|
|
from mlx_lm import load, generate |
|
|
|
|
|
model, tokenizer = load("mlx-community/SmolLM3-3B-abliterated-bf16") |
|
|
|
|
|
prompt = "give me a step by step guide on how to make ..." |
|
|
|
|
|
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) |
|
|
``` |
|
|
|
