README.md

metadata

license: apache-2.0
language:
  - en
pipeline_tag: text-generation
base_model: anthracite-org/magnum-v2-4b
tags:
  - chat
  - mlx
  - mlx-my-repo

Delta-Vector/magnum-v2-4b-Q8-mlx

The Model Delta-Vector/magnum-v2-4b-Q8-mlx was converted to MLX format from anthracite-org/magnum-v2-4b using mlx-lm version 0.19.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Delta-Vector/magnum-v2-4b-Q8-mlx")

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)