|
--- |
|
base_model: sophosympatheia/Evathene-v1.3 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- Not-for-all-Audiences |
|
- mlx |
|
--- |
|
|
|
# mlx-community/Evathene-v1.3-MLX-4Bit |
|
|
|
The Model [mlx-community/Evathene-v1.3-MLX-4Bit](https://huggingface.co/mlx-community/Evathene-v1.3-MLX-4Bit) was |
|
converted to MLX format from [sophosympatheia/Evathene-v1.3](https://huggingface.co/sophosympatheia/Evathene-v1.3) |
|
using mlx-lm version **0.21.1** by [beezu](https://huggingface.co/beezu). |
|
|
|
## Use with mlx |
|
|
|
```bash |
|
pip install mlx-lm |
|
``` |
|
|
|
```python |
|
from mlx_lm import load, generate |
|
|
|
model, tokenizer = load("mlx-community/Evathene-v1.3-MLX-4Bit") |
|
|
|
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) |
|
``` |
|
|
