TensorVizion/MiMo-V2.6-Distill-Qwen-9B-mlx-2Bit
The Model TensorVizion/MiMo-V2.6-Distill-Qwen-9B-mlx-2Bit was converted to MLX format from XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B using mlx-lm version 0.31.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("TensorVizion/MiMo-V2.6-Distill-Qwen-9B-mlx-2Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)