43 lines
978 B
Markdown
43 lines
978 B
Markdown
---
|
|
license: mit
|
|
language:
|
|
- en
|
|
base_model: WeiboAI/VibeThinker-3B
|
|
tags:
|
|
- math
|
|
- code
|
|
- reasoning
|
|
- gpqa
|
|
- instruction-following
|
|
- mlx
|
|
- mlx-my-repo
|
|
pipeline_tag: text-generation
|
|
library_name: transformers
|
|
---
|
|
|
|
# usermma/VibeThinker-3B-mlx-fp16
|
|
|
|
The Model [usermma/VibeThinker-3B-mlx-fp16](https://huggingface.co/usermma/VibeThinker-3B-mlx-fp16) was converted to MLX format from [WeiboAI/VibeThinker-3B](https://huggingface.co/WeiboAI/VibeThinker-3B) using mlx-lm version **0.31.2**.
|
|
|
|
## Use with mlx
|
|
|
|
```bash
|
|
pip install mlx-lm
|
|
```
|
|
|
|
```python
|
|
from mlx_lm import load, generate
|
|
|
|
model, tokenizer = load("usermma/VibeThinker-3B-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)
|
|
```
|