Trinity-337B-W4A16 / quantization_config.json
0xSero's picture
W4A16 RTN quantization (216/256 experts, 166GB)
8032f24 verified
{
"bits": 4,
"data_type": "int",
"group_size": 128,
"sym": true,
"batch_size": 1,
"iters": 0,
"low_gpu_mem_usage": true,
"autoround_version": "0.12.2",
"quant_method": "auto-round",
"packing_format": "auto_round:auto_gptq",
"extra_config": {
"model.layers.6.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.7.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.8.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.9.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.10.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.11.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.12.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.13.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.14.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.15.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.16.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.17.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.18.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.19.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.20.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.21.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.22.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.23.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.24.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.25.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.26.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.27.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.28.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.29.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.30.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.31.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.32.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.33.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.34.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.35.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.36.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.37.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.38.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.39.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.40.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.41.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.42.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.43.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.44.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.45.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.46.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.47.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.48.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.49.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.50.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.51.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.52.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.53.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.54.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.55.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.56.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.57.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.58.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
},
"model.layers.59.mlp.router.gate": {
"bits": 16,
"data_type": "fp"
}
}
}