GLM-4.7-Flash-impotent-heresy-mlx-8Bit

MuXodious/GLM-4.7-Flash-impotent-heresy-mlx-8Bit

This model MuXodious/GLM-4.7-Flash-impotent-heresy-mlx-8Bit was converted to MLX format from MuXodious/GLM-4.7-Flash-impotent-heresy using mlx-lm version 0.30.5.

Notice: The quant has been regenerated with mlx-lm @git+96699e6, which includes critical fixes for GLM 4.7 Flash.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("MuXodious/GLM-4.7-Flash-impotent-heresy-mlx-8Bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)