cs2764/Huihui-GLM-4.7-Flash-abliterated-mlx-8Bit

The Model cs2764/Huihui-GLM-4.7-Flash-abliterated-mlx-8Bit was converted to MLX format from huihui-ai/Huihui-GLM-4.7-Flash-abliterated using mlx-lm version 0.30.4.

Quantization Details

This model was converted with the following quantization settings:

• Quantization Strategy: 8-bit quantization
• Average bits per weight: 8.502

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cs2764/Huihui-GLM-4.7-Flash-abliterated-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)