metadata
tags:
- unsloth
- mlx
- mlx-my-repo
base_model: unsloth/GLM-4.7
language:
- en
- zh
library_name: transformers
license: mit
pipeline_tag: text-generation
worstje/GLM-4.7-mlx-4Bit
The Model worstje/GLM-4.7-mlx-4Bit was converted to MLX format from unsloth/GLM-4.7 using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("worstje/GLM-4.7-mlx-4Bit")
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)