File size: 1,895 Bytes
1992096 |
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 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
{
"dtype": "int8_int8_int8",
"input_info": null,
"optimum_version": "1.26.1",
"quantization_config": {
"dataset": "contextual",
"ignored_scope": null,
"num_samples": 200,
"processor": null,
"quantization_configs": {
"lm_model": {
"bits": 8,
"dataset": null,
"dtype": "int8",
"fast_bias_correction": true,
"ignored_scope": null,
"model_type": "transformer",
"num_samples": null,
"overflow_fix": "disable",
"processor": null,
"smooth_quant_alpha": null,
"sym": false,
"tokenizer": null,
"trust_remote_code": false
},
"text_embeddings_model": {
"all_layers": null,
"backup_precision": null,
"bits": 8,
"dataset": null,
"dtype": "int8",
"gptq": null,
"group_size": -1,
"ignored_scope": null,
"lora_correction": null,
"num_samples": null,
"processor": null,
"quant_method": "default",
"ratio": 1.0,
"scale_estimation": null,
"sensitivity_metric": null,
"sym": false,
"tokenizer": null,
"trust_remote_code": false
},
"vision_embeddings_model": {
"all_layers": null,
"backup_precision": null,
"bits": 8,
"dataset": null,
"dtype": "int8",
"gptq": null,
"group_size": -1,
"ignored_scope": null,
"lora_correction": null,
"num_samples": null,
"processor": null,
"quant_method": "default",
"ratio": 1.0,
"scale_estimation": null,
"sensitivity_metric": null,
"sym": false,
"tokenizer": null,
"trust_remote_code": false
}
},
"tokenizer": null,
"trust_remote_code": false
},
"save_onnx_model": false,
"transformers_version": "4.52.4"
}
|