metadata
license: mit
language:
- zh
- en
pipeline_tag: text-generation
library_name: mlx
tags:
- mlx
base_model: THUDM/GLM-4-32B-Base-0414
mlx-community/GLM-4-32B-Base-0414-8bit
This model mlx-community/GLM-4-32B-Base-0414-8bit was converted to MLX format from THUDM/GLM-4-32B-Base-0414 using mlx-lm version 0.23.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/GLM-4-32B-Base-0414-8bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)