metadata
language:
- en
library_name: transformers
tags:
- glm
- MOE
- pruning
- compression
- mlx
- mlx-my-repo
license: mit
name: cerebras/GLM-4.5-Air-REAP-82B-A12B
description: >
This model was obtained by uniformly pruning 25% of experts in GLM-4.5-Air
using the REAP method.
readme: |
https://huggingface.co/cerebras/GLM-4.5-Air-REAP-82B-A12B/main/README.md
license_link: https://huggingface.co/zai-org/GLM-4.5-Air/blob/main/LICENSE
pipeline_tag: text-generation
base_model: cerebras/GLM-4.5-Air-REAP-82B-A12B
manasmisra/GLM-4.5-Air-REAP-82B-A12B-mlx-4Bit
The Model manasmisra/GLM-4.5-Air-REAP-82B-A12B-mlx-4Bit was converted to MLX format from cerebras/GLM-4.5-Air-REAP-82B-A12B using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("manasmisra/GLM-4.5-Air-REAP-82B-A12B-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)