metadata
license: apache-2.0
base_model: 0xSero/MiniMax-M2.1-REAP-40
tags:
- minimax
- moe
- reap
- pruned
- text-generation
- mlx
library_name: mlx
pipeline_tag: text-generation
mlx-community/MiniMax-M2.1-REAP-40-4bit
This model mlx-community/MiniMax-M2.1-REAP-40-4bit was converted to MLX format from 0xSero/MiniMax-M2.1-REAP-40 using mlx-lm version 0.30.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/MiniMax-M2.1-REAP-40-4bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)