Modelpublic

CallMcMargin/Qwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-mxfp4-qgroup32-mixed_3_6

sourceHugging Faceapache-2.0updated 11mo agoView on Hugging Face

0likes16downloads

Model Card

CallMcMargin/Qwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-mxfp4-qgroup32-mixed36

This model CallMcMargin/Qwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-mxfp4-qgroup32-mixed_3_6 was converted to MLX format from huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated using mlx-lm version 0.28.3.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("CallMcMargin/Qwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-mxfp4-qgroup32-mixed_3_6")

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)