README.md

metadata

license: apache-2.0
datasets:
  - open-r1/Mixture-of-Thoughts
language:
  - en
base_model: open-r1/OpenR1-Distill-7B
library_name: mlx
tags:
  - mlx
pipeline_tag: text-generation

mlx-community/OpenR1-Distill-7B-4bit

This model mlx-community/OpenR1-Distill-7B-4bit was converted to MLX format from open-r1/OpenR1-Distill-7B using mlx-lm version 0.24.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/OpenR1-Distill-7B-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)