bobtk's picture
391005ed2ef3abaf1355dc7c4fca8d1e9fd27859d9bf7c64eab781793d4dea30
1dd75d2 verified
|
raw
history blame
642 Bytes
---
language:
- ja
- en
license: apache-2.0
library_name: transformers
tags:
- japanese
- mlx
---
# mlx-community/Tanuki-8B-dpo-v1.0-8bit
The Model [mlx-community/Tanuki-8B-dpo-v1.0-8bit](https://huggingface.co/mlx-community/Tanuki-8B-dpo-v1.0-8bit) was converted to MLX format from [weblab-GENIAC/Tanuki-8B-dpo-v1.0](https://huggingface.co/weblab-GENIAC/Tanuki-8B-dpo-v1.0) using mlx-lm version **0.18.0**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Tanuki-8B-dpo-v1.0-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```