metadata
language:
- en
- zh
library_name: transformers
license: mit
pipeline_tag: text-generation
tags:
- mlx
base_model: zai-org/GLM-4.7
jesusoctavioas/GLM-4.7-mlx-2Bit
The Model jesusoctavioas/GLM-4.7-mlx-2Bit was converted to MLX format from zai-org/GLM-4.7 using mlx-lm version 0.29.1.
Use with mlx
python -m venv mlx-venv
# then activate the virtual enviroment if needed.
source mlx-venv/bin/activate
# then install mlx.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("jesusoctavioas/GLM-4.7-mlx-2Bit")
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)