base_model: llmfan46/MiniMax-M2.7-BF16-ultra-uncensored-heretic pipeline_tag: text-generation license: other license_name: other license_link: https://github.com/MiniMax-AI/MiniMax-M2.7/blob/main/LICENSE library_name: transformers tags:

• heretic
• uncensored
• decensored
• abliterated
• ara
• mlx
• mlx-my-repo

cookietimeh/MiniMax-M2.7-BF16-ultra-uncensored-heretic-mlx-4Bit

The Model cookietimeh/MiniMax-M2.7-BF16-ultra-uncensored-heretic-mlx-4Bit was converted to MLX format from llmfan46/MiniMax-M2.7-BF16-ultra-uncensored-heretic using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cookietimeh/MiniMax-M2.7-BF16-ultra-uncensored-heretic-mlx-4Bit")

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)