metadata
license: mit
datasets:
- zerofata/Instruct-Anime
- zerofata/Roleplay-Anime-Characters
- zerofata/Instruct-Anime-CreativeWriting
- zerofata/Summaries-Anime-FandomPages
base_model: zerofata/GLM-4.5-Iceblink-106B-A12B
tags:
- mlx
Wwayu/GLM-4.5-Iceblink-106B-A12B-mlx-4Bit
The Model Wwayu/GLM-4.5-Iceblink-106B-A12B-mlx-4Bit was converted to MLX format from zerofata/GLM-4.5-Iceblink-106B-A12B using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Wwayu/GLM-4.5-Iceblink-106B-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)