Mistral (Mamba) Codestral
Collection
8 items
•
Updated
The Model mlx-community/Codestral-22B-v0.1-8bit was converted to MLX format from bullerwins/Codestral-22B-v0.1-hf using mlx-lm version 0.14.0.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Codestral-22B-v0.1-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)