mlx-community/ArrowPro-7B-KUJIRA-4bit
The Model mlx-community/ArrowPro-7B-KUJIRA-4bit was converted to MLX format from DataPilot/ArrowPro-7B-KUJIRA using mlx-lm version 0.15.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/ArrowPro-7B-KUJIRA-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 7
Hardware compatibility
Log In
to add your hardware
Quantized
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support