README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
  - mlx
  - mlx-my-repo
license: apache-2.0
base_model: MarinaraSpaghetti/NemoMix-Unleashed-12B

Cozmicalz/NemoMix-Unleashed-12B-mlx-3Bit

The Model Cozmicalz/NemoMix-Unleashed-12B-mlx-3Bit was converted to MLX format from MarinaraSpaghetti/NemoMix-Unleashed-12B using mlx-lm version 0.22.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Cozmicalz/NemoMix-Unleashed-12B-mlx-3Bit")

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)