README.md

metadata

license: apache-2.0
thumbnail: >-
  https://cdn-uploads.huggingface.co/production/uploads/6625f4a8a8d1362ebcc3851a/albSlnUy9dPVGVuLlsBua.jpeg
language:
  - en
base_model: ArliAI/QwQ-32B-ArliAI-RpR-v1
tags:
  - mlx

Fmuaddib/QwQ-32B-ArliAI-RpR-v1-mlx-8Bit

The Model Fmuaddib/QwQ-32B-ArliAI-RpR-v1-mlx-8Bit was converted to MLX format from ArliAI/QwQ-32B-ArliAI-RpR-v1 using mlx-lm version 0.22.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Fmuaddib/QwQ-32B-ArliAI-RpR-v1-mlx-8Bit")

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)