awhiteside/QwQ-32B-abliterated-3bit

The Model awhiteside/QwQ-32B-abliterated-3bit was converted to MLX format from huihui-ai/QwQ-32B-abliterated using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("awhiteside/QwQ-32B-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)

README.md说明 / 使用方法

license: apache-2.0 license_link: https://huggingface.co/huihui-ai/QwQ-32B-abliterated/blob/main/LICENSE language:

en pipeline_tag: text-generation base_model: huihui-ai/QwQ-32B-abliterated tags:
chat
abliterated
uncensored
mlx
mlx-my-repo

awhiteside/QwQ-32B-abliterated-3bit

The Model awhiteside/QwQ-32B-abliterated-3bit was converted to MLX format from huihui-ai/QwQ-32B-abliterated using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("awhiteside/QwQ-32B-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)