metadata
language:
- en
- zh
library_name: mlx
license: mit
pipeline_tag: text-generation
base_model: zai-org/GLM-4.5
tags:
- mlx
sjug/GLM-4.5-MLX-9bit
This model sjug/GLM-4.5-MLX-9bit was converted to MLX format from zai-org/GLM-4.5 using mlx-lm version 0.26.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("sjug/GLM-4.5-MLX-9bit")
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)