|
--- |
|
language: |
|
- en |
|
license: other |
|
tags: |
|
- chat |
|
- mlx |
|
license_name: tongyi-qianwen-research |
|
license_link: https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat/blob/main/LICENSE |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# mlx-community/Qwen1.5-1.8B-Chat-4bit |
|
This model was converted to MLX format from [`Qwen/Qwen1.5-1.8B-Chat`](). |
|
Refer to the [original model card](https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat) for more details on the model. |
|
## Use with mlx |
|
|
|
```bash |
|
pip install mlx-lm |
|
``` |
|
|
|
```python |
|
from mlx_lm import load, generate |
|
|
|
model, tokenizer = load("mlx-community/Qwen1.5-1.8B-Chat-4bit") |
|
|
|
prompt = "hello" |
|
|
|
messages = [ |
|
{"role": "system", "content": "You are a helpful assistant."}, |
|
{"role": "user", "content": prompt} |
|
] |
|
|
|
text = tokenizer.apply_chat_template( |
|
messages, |
|
tokenize=False, |
|
add_generation_prompt=True |
|
) |
|
|
|
response = generate(model, tokenizer, prompt=text, verbose=True, max_tokens=200) |
|
|
|
``` |
|
|