zephyr-7b-beta-marlin / quantize_config.json
robertgshaw2's picture
added models
764bad9
{
"bits": 4,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": false,
"static_groups": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": "zephyr-chat-gptq-g128",
"model_file_base_name": "model",
"is_marlin_format": true,
"quant_method": "gptq"
}