File size: 1,483 Bytes
4007de7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
{
"bits": 4,
"group_size": 128,
"sym": true,
"data_type": "int",
"enable_quanted_input": true,
"enable_minmax_tuning": true,
"seqlen": 2048,
"batch_size": 8,
"scale_dtype": "torch.float16",
"lr": 0.005,
"minmax_lr": 0.005,
"gradient_accumulate_steps": 1,
"iters": 200,
"amp": true,
"nsamples": 128,
"low_gpu_mem_usage": false,
"to_quant_block_names": [
[
"model.text_model.layers.0",
"model.text_model.layers.1",
"model.text_model.layers.2",
"model.text_model.layers.3",
"model.text_model.layers.4",
"model.text_model.layers.5",
"model.text_model.layers.6",
"model.text_model.layers.7",
"model.text_model.layers.8",
"model.text_model.layers.9",
"model.text_model.layers.10",
"model.text_model.layers.11",
"model.text_model.layers.12",
"model.text_model.layers.13",
"model.text_model.layers.14",
"model.text_model.layers.15",
"model.text_model.layers.16",
"model.text_model.layers.17",
"model.text_model.layers.18",
"model.text_model.layers.19",
"model.text_model.layers.20",
"model.text_model.layers.21",
"model.text_model.layers.22",
"model.text_model.layers.23"
]
],
"enable_norm_bias_tuning": false,
"autoround_version": "0.4.2.dev",
"block_name_to_quantize": "model.text_model.layers",
"quant_method": "gptq",
"desc_act": false,
"true_sequential": false,
"damp_percent": 0.01
} |