license: apache-2.0
license_link: https://huggingface.co/huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterate/blob/main/LICENSE
language:

• en
  base_model: huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated
  pipeline_tag: text-generation
  library_name: transformers
  tags:
• code
• codeqwen
• chat
• qwen
• qwen-coder
• abliterated
• uncensored
• mlx
• mlx-my-repo

mlx-community/Qwen2.5-Coder-32B-Instruct-abliterated-3bit

The Model mlx-community/Qwen2.5-Coder-32B-Instruct-abliterated-3bit was converted to MLX format from huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-abliterated-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)