stockmark-100b-8bit / README.md
bobtk's picture
f990bf963e17f9789e369ad514b611a887f826a5650a6896e80d3677a159a4aa
4cac3f6 verified
|
raw
history blame
567 Bytes
---
language:
- ja
- en
license: mit
library_name: transformers
tags:
- mlx
---
# mlx-community/stockmark-100b-8bit
This model was converted to MLX format from [`stockmark/stockmark-100b`]() using mlx-lm version **0.12.1**.
Refer to the [original model card](https://huggingface.co/stockmark/stockmark-100b) 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/stockmark-100b-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```