k2rks/Yi-Coder-9B-Chat-mlx-4bit

The Model k2rks/Yi-Coder-9B-Chat-mlx-4bit was converted to MLX format from 01-ai/Yi-Coder-9B-Chat using mlx-lm version 0.18.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("k2rks/Yi-Coder-9B-Chat-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)