MLX
Safetensors
mistral
Not-For-All-Audiences
nsfw
8-bit precision
Lumimaid-v0.2-12B / README.md
morgul's picture
88ecf17b61123a17245801641a84e1abba79fe8d3fe4b81d94616b4d1c553b81
876eafc verified
|
raw
history blame
893 Bytes
---
base_model: NeverSleep/Lumimaid-v0.2-12B
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- nsfw
- mlx
---
# mlx-community/Lumimaid-v0.2-12B
The Model [mlx-community/Lumimaid-v0.2-12B](https://huggingface.co/mlx-community/Lumimaid-v0.2-12B) was converted to MLX format from [NeverSleep/Lumimaid-v0.2-12B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-12B) using mlx-lm version **0.19.0**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Lumimaid-v0.2-12B")
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)
```