|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- bias-detection |
|
|
- news-analysis |
|
|
- media-bias |
|
|
- journalism |
|
|
- content-analysis |
|
|
- mlx |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-generation |
|
|
base_model: EmergentMethods/Qwen3-4B-BiasExpert |
|
|
library_name: mlx |
|
|
--- |
|
|
|
|
|
# Qwen3-4B-BiasExpert-dwq6-mlx |
|
|
|
|
|
find and address bias in your code |
|
|
|
|
|
This model [Qwen3-4B-BiasExpert-dwq6-mlx](https://huggingface.co/Qwen3-4B-BiasExpert-dwq6-mlx) was |
|
|
converted to MLX format from [EmergentMethods/Qwen3-4B-BiasExpert](https://huggingface.co/EmergentMethods/Qwen3-4B-BiasExpert) |
|
|
using mlx-lm version **0.26.0**. |
|
|
|
|
|
## Use with mlx |
|
|
|
|
|
```bash |
|
|
pip install mlx-lm |
|
|
``` |
|
|
|
|
|
```python |
|
|
from mlx_lm import load, generate |
|
|
|
|
|
model, tokenizer = load("Qwen3-4B-BiasExpert-dwq6-mlx") |
|
|
|
|
|
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) |
|
|
``` |
|
|
|
