README.md

metadata

license: apache-2.0
language:
  - en
tags:
  - chat
  - mlx
pipeline_tag: text-generation
library_name: transformers
datasets:
  - anthracite-org/c2_logs_32k_llama3_qwen2_v1.2
  - anthracite-org/kalo-opus-instruct-22k-no-refusal
  - lodrick-the-lafted/kalo-opus-instruct-3k-filtered
  - anthracite-org/nopm_claude_writing_fixed
  - anthracite-org/kalo_opus_misc_240827
  - anthracite-org/kalo_misc_part2
base_model: anthracite-org/magnum-v4-72b

mlx-community/magnum-v4-72b-4bit

The Model mlx-community/magnum-v4-72b-4bit was converted to MLX format from anthracite-org/magnum-v4-72b using mlx-lm version 0.20.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/magnum-v4-72b-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)