Modelpublic

zimengxiong/Qwopus-GLM-18B-Healed-MLX-8bit

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face

0likes13downloads

Model Card

zimengxiong/Qwopus-GLM-18B-Healed-MLX-8bit

This model zimengxiong/Qwopus-GLM-18B-Healed-MLX-8bit was converted to MLX format from KyleHessling1/Qwopus-GLM-18B-Healed using mlx-lm version 0.31.2.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("zimengxiong/Qwopus-GLM-18B-Healed-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)