|
|
--- |
|
|
base_model: Skywork/Skywork-OR1-32B-Preview |
|
|
tags: |
|
|
- mlx |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
|
|
|
# YuHaaa/Skywork-OR1-32B-Preview-mlx-6Bit |
|
|
|
|
|
The Model [YuHaaa/Skywork-OR1-32B-Preview-mlx-6Bit](https://huggingface.co/YuHaaa/Skywork-OR1-32B-Preview-mlx-6Bit) was converted to MLX format from [Skywork/Skywork-OR1-32B-Preview](https://huggingface.co/Skywork/Skywork-OR1-32B-Preview) using mlx-lm version **0.22.1**. |
|
|
|
|
|
## Use with mlx |
|
|
|
|
|
```bash |
|
|
pip install mlx-lm |
|
|
``` |
|
|
|
|
|
```python |
|
|
from mlx_lm import load, generate |
|
|
|
|
|
model, tokenizer = load("YuHaaa/Skywork-OR1-32B-Preview-mlx-6Bit") |
|
|
|
|
|
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) |
|
|
``` |
