mlx-community/Yi-1.5-9B-Chat-4bit

The Model mlx-community/Yi-1.5-9B-Chat-4bit was converted to MLX format from 01-ai/Yi-1.5-9B-Chat using mlx-lm version 0.13.0.

Model added by Prince Canuma.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Yi-1.5-9B-Chat-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)