Mistral
Collection
21 items
•
Updated
•
8
The Model mlx-community/Mistral-7B-v0.3-4bit was converted to MLX format from mistralai/Mistral-7B-v0.3 using mlx-lm version 0.13.1.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Mistral-7B-v0.3-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)