mlx-community/ilsp-Meltemi-7B-Instruct-v1-4bit
This model was converted to MLX format from ilsp/Meltemi-7B-Instruct-v1 using mlx-lm version 0.4.0.
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("mlx-community/ilsp-Meltemi-7B-Instruct-v1-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 4
Hardware compatibility
Log In
to add your hardware
Quantized