nishide-dev/suzume-poc-mlx-4bit
This model was converted to MLX format from alfredplpl/suzume-poc using mlx-lm version 0.7.0.
Refer to the original model card for more details on the model.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("nishide-dev/suzume-poc-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 5
Model size
0.8B params
Tensor type
F16
·
U32
·
Hardware compatibility
Log In
to add your hardware
Quantized