README.md

metadata

library_name: mlx
pipeline_tag: text-generation
tags:
  - transformers
  - mlx
license: other
license_name: modified-mit
license_link: https://github.com/MiniMax-AI/MiniMax-M2.1/blob/main/LICENSE
base_model:
  - MiniMaxAI/MiniMax-M2.1

mlx-community/MiniMax-M2.1-4bit

This model mlx-community/MiniMax-M2.1-4bit was converted to MLX format from MiniMaxAI/MiniMax-M2.1 using mlx-lm version 0.29.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/MiniMax-M2.1-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)