MiniMax-M2.5-4bit / README.md
async0x42's picture
Add files using upload-large-folder tool
0c0bf33 verified
metadata
tags:
  - unsloth
  - mlx
base_model: unsloth/minimax-m2.5
pipeline_tag: text-generation
license: other
license_name: modified-mit
license_link: https://github.com/MiniMax-AI/MiniMax-M2.5/blob/main/LICENSE
library_name: mlx

async0x42/unsloth_MiniMax-M2.5-4bit

This model async0x42/unsloth_MiniMax-M2.5-4bit was converted to MLX format from unsloth/minimax-m2.5 using mlx-lm version 0.30.7.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("async0x42/unsloth_MiniMax-M2.5-4bit")

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)