cmcmaster/Qwen2-1.5B-Instruct-rheum-pretrain-mlx-4bit

The Model cmcmaster/Qwen2-1.5B-Instruct-rheum-pretrain-mlx-4bit was converted to MLX format from cmcmaster/Qwen2-1.5B-Instruct-rheum-pretrain using mlx-lm version 0.15.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cmcmaster/Qwen2-1.5B-Instruct-rheum-pretrain-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)