mlx-community
/

Mistral-Small-3.2-24B-Instruct-2506-q8

Text Generation

8-bit precision

Model card Files Files and versions

Mistral-Small-3.2-24B-Instruct-2506-q8 / generation_config.json

kweg's picture

Add files using upload-large-folder tool

1db8354 verified 1 day ago

history blame contribute delete

135 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.52.4",
	"temperature": 0.15,
	}