GLM-4.7-Flash-PRISM-mlx-4bit / generation_config.json
shieldstackllc's picture
Add GLM-4.7-Flash-PRISM MLX 4-bit quantization by vMLX
459d2af verified
{
"_from_model_config": true,
"eos_token_id": [
154820,
154827,
154829
],
"pad_token_id": 154820,
"temperature": 1.0,
"transformers_version": "5.0.0.dev0"
}