36 lines
1.0 KiB
Markdown
36 lines
1.0 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
license: apache-2.0
|
||
|
|
license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
base_model: Qwen/Qwen3-4B-Instruct-2507
|
||
|
|
tags:
|
||
|
|
- mlx
|
||
|
|
---
|
||
|
|
|
||
|
|
# BlueMoonlight/Qwen3-4B-Instruct-2507-mlx-fp16
|
||
|
|
|
||
|
|
The Model [BlueMoonlight/Qwen3-4B-Instruct-2507-mlx-fp16](https://huggingface.co/BlueMoonlight/Qwen3-4B-Instruct-2507-mlx-fp16) was converted to MLX format from [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) using mlx-lm version **0.29.1**.
|
||
|
|
|
||
|
|
## Use with mlx
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install mlx-lm
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
from mlx_lm import load, generate
|
||
|
|
|
||
|
|
model, tokenizer = load("BlueMoonlight/Qwen3-4B-Instruct-2507-mlx-fp16")
|
||
|
|
|
||
|
|
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)
|
||
|
|
```
|