README.md

metadata

language:
  - en
library_name: transformers
tags:
  - mergekit
  - merge
  - mlx
base_model: royallab/MN-LooseCannon-12B-v2

mlx-community/royallab_MN-LooseCannon-12B-v2

The Model mlx-community/royallab_MN-LooseCannon-12B-v2 was converted to MLX format from royallab/MN-LooseCannon-12B-v2 using mlx-lm version 0.19.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/royallab_MN-LooseCannon-12B-v2")

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)