English
rk-transformers
bert
exbert
rknn
rockchip
npu
rk3588
bert-base-uncased / rknn.json
eacortes's picture
Upload folder using huggingface_hub
4113b79 verified
{
"model.rknn": {
"model_input_names": [
"input_ids",
"attention_mask",
"token_type_ids"
],
"batch_size": 1,
"max_seq_length": 512,
"float_dtype": "float16",
"target_platform": "rk3588",
"single_core_mode": false,
"mean_values": null,
"std_values": null,
"custom_string": null,
"inputs_yuv_fmt": null,
"dynamic_input": null,
"opset": 18,
"task": "fill-mask",
"quantization": {
"do_quantization": false,
"dataset_name": null,
"dataset_subset": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_columns": null,
"quantized_dtype": "w8a8",
"quantized_algorithm": "normal",
"quantized_method": "channel",
"quantized_hybrid_level": 0,
"quant_img_RGB2BGR": false,
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null
},
"optimization": {
"optimization_level": 0,
"enable_flash_attention": true,
"remove_weight": false,
"compress_weight": false,
"remove_reshape": false,
"sparse_infer": false,
"model_pruning": false
}
},
"rknn/model_o1.rknn": {
"model_input_names": [
"input_ids",
"attention_mask",
"token_type_ids"
],
"batch_size": 1,
"max_seq_length": 512,
"float_dtype": "float16",
"target_platform": "rk3588",
"single_core_mode": false,
"mean_values": null,
"std_values": null,
"custom_string": null,
"inputs_yuv_fmt": null,
"dynamic_input": null,
"opset": 18,
"task": "fill-mask",
"quantization": {
"do_quantization": false,
"dataset_name": null,
"dataset_subset": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_columns": null,
"quantized_dtype": "w8a8",
"quantized_algorithm": "normal",
"quantized_method": "channel",
"quantized_hybrid_level": 0,
"quant_img_RGB2BGR": false,
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null
},
"optimization": {
"optimization_level": 1,
"enable_flash_attention": true,
"remove_weight": false,
"compress_weight": false,
"remove_reshape": false,
"sparse_infer": false,
"model_pruning": false
}
},
"rknn/model_o2.rknn": {
"model_input_names": [
"input_ids",
"attention_mask",
"token_type_ids"
],
"batch_size": 1,
"max_seq_length": 512,
"float_dtype": "float16",
"target_platform": "rk3588",
"single_core_mode": false,
"mean_values": null,
"std_values": null,
"custom_string": null,
"inputs_yuv_fmt": null,
"dynamic_input": null,
"opset": 18,
"task": "fill-mask",
"quantization": {
"do_quantization": false,
"dataset_name": null,
"dataset_subset": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_columns": null,
"quantized_dtype": "w8a8",
"quantized_algorithm": "normal",
"quantized_method": "channel",
"quantized_hybrid_level": 0,
"quant_img_RGB2BGR": false,
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null
},
"optimization": {
"optimization_level": 2,
"enable_flash_attention": true,
"remove_weight": false,
"compress_weight": false,
"remove_reshape": false,
"sparse_infer": false,
"model_pruning": false
}
},
"rknn/model_o3.rknn": {
"model_input_names": [
"input_ids",
"attention_mask",
"token_type_ids"
],
"batch_size": 1,
"max_seq_length": 512,
"float_dtype": "float16",
"target_platform": "rk3588",
"single_core_mode": false,
"mean_values": null,
"std_values": null,
"custom_string": null,
"inputs_yuv_fmt": null,
"dynamic_input": null,
"opset": 18,
"task": "fill-mask",
"quantization": {
"do_quantization": false,
"dataset_name": null,
"dataset_subset": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_columns": null,
"quantized_dtype": "w8a8",
"quantized_algorithm": "normal",
"quantized_method": "channel",
"quantized_hybrid_level": 0,
"quant_img_RGB2BGR": false,
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null
},
"optimization": {
"optimization_level": 3,
"enable_flash_attention": true,
"remove_weight": false,
"compress_weight": false,
"remove_reshape": false,
"sparse_infer": false,
"model_pruning": false
}
},
"rknn/model_w8a8.rknn": {
"model_input_names": [
"input_ids",
"attention_mask",
"token_type_ids"
],
"batch_size": 1,
"max_seq_length": 512,
"float_dtype": "float16",
"target_platform": "rk3588",
"single_core_mode": false,
"mean_values": null,
"std_values": null,
"custom_string": null,
"inputs_yuv_fmt": null,
"dynamic_input": null,
"opset": 18,
"task": "fill-mask",
"quantization": {
"do_quantization": true,
"dataset_name": "sentence-transformers/natural-questions",
"dataset_subset": null,
"dataset_size": 2048,
"dataset_split": [
"train"
],
"dataset_columns": [
"answer"
],
"quantized_dtype": "w8a8",
"quantized_algorithm": "normal",
"quantized_method": "channel",
"quantized_hybrid_level": 0,
"quant_img_RGB2BGR": false,
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null
},
"optimization": {
"optimization_level": 0,
"enable_flash_attention": true,
"remove_weight": false,
"compress_weight": false,
"remove_reshape": false,
"sparse_infer": false,
"model_pruning": false
}
},
"model_b4_s512.rknn": {
"model_input_names": [
"input_ids",
"attention_mask",
"token_type_ids"
],
"batch_size": 4,
"max_seq_length": 512,
"float_dtype": "float16",
"target_platform": "rk3588",
"single_core_mode": false,
"mean_values": null,
"std_values": null,
"custom_string": null,
"inputs_yuv_fmt": null,
"dynamic_input": null,
"opset": 18,
"task": "fill-mask",
"quantization": {
"do_quantization": false,
"dataset_name": null,
"dataset_subset": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_columns": null,
"quantized_dtype": "w8a8",
"quantized_algorithm": "normal",
"quantized_method": "channel",
"quantized_hybrid_level": 0,
"quant_img_RGB2BGR": false,
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null
},
"optimization": {
"optimization_level": 0,
"enable_flash_attention": true,
"remove_weight": false,
"compress_weight": false,
"remove_reshape": false,
"sparse_infer": false,
"model_pruning": false
}
},
"model_b1_s256.rknn": {
"model_input_names": [
"input_ids",
"attention_mask",
"token_type_ids"
],
"batch_size": 1,
"max_seq_length": 256,
"float_dtype": "float16",
"target_platform": "rk3588",
"single_core_mode": false,
"mean_values": null,
"std_values": null,
"custom_string": null,
"inputs_yuv_fmt": null,
"dynamic_input": null,
"opset": 18,
"task": "auto",
"quantization": {
"do_quantization": false,
"dataset_name": null,
"dataset_subset": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_columns": null,
"quantized_dtype": "w8a8",
"quantized_algorithm": "normal",
"quantized_method": "channel",
"quantized_hybrid_level": 0,
"quant_img_RGB2BGR": false,
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null
},
"optimization": {
"optimization_level": 0,
"enable_flash_attention": true,
"remove_weight": false,
"compress_weight": false,
"remove_reshape": false,
"sparse_infer": false,
"model_pruning": false
}
},
"model_b4_s256.rknn": {
"model_input_names": [
"input_ids",
"attention_mask",
"token_type_ids"
],
"batch_size": 4,
"max_seq_length": 256,
"float_dtype": "float16",
"target_platform": "rk3588",
"single_core_mode": false,
"mean_values": null,
"std_values": null,
"custom_string": null,
"inputs_yuv_fmt": null,
"dynamic_input": null,
"opset": 18,
"task": "auto",
"quantization": {
"do_quantization": false,
"dataset_name": null,
"dataset_subset": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_columns": null,
"quantized_dtype": "w8a8",
"quantized_algorithm": "normal",
"quantized_method": "channel",
"quantized_hybrid_level": 0,
"quant_img_RGB2BGR": false,
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null
},
"optimization": {
"optimization_level": 0,
"enable_flash_attention": true,
"remove_weight": false,
"compress_weight": false,
"remove_reshape": false,
"sparse_infer": false,
"model_pruning": false
}
}
}