ModernBERT-base / config.json
eacortes's picture
Upload folder using huggingface_hub
12172b7
{
"architectures": [
"ModernBertForMaskedLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 50281,
"classifier_activation": "gelu",
"classifier_bias": false,
"classifier_dropout": 0.0,
"classifier_pooling": "mean",
"cls_token_id": 50281,
"decoder_bias": true,
"deterministic_flash_attn": false,
"embedding_dropout": 0.0,
"eos_token_id": 50282,
"global_attn_every_n_layers": 3,
"global_rope_theta": 160000.0,
"gradient_checkpointing": false,
"hidden_activation": "gelu",
"hidden_size": 768,
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 1152,
"layer_norm_eps": 1e-05,
"local_attention": 128,
"local_rope_theta": 10000.0,
"max_position_embeddings": 8192,
"mlp_bias": false,
"mlp_dropout": 0.0,
"model_type": "modernbert",
"norm_bias": false,
"norm_eps": 1e-05,
"num_attention_heads": 12,
"num_hidden_layers": 22,
"pad_token_id": 50283,
"position_embedding_type": "absolute",
"repad_logits_with_grad": false,
"rknn": {
"model.rknn": {
"batch_size": 1,
"custom_string": null,
"dynamic_input": null,
"float_dtype": "float16",
"inputs_yuv_fmt": null,
"max_seq_length": 512,
"mean_values": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"opset": 19,
"optimization": {
"compress_weight": false,
"enable_flash_attention": true,
"model_pruning": false,
"optimization_level": 0,
"remove_reshape": false,
"remove_weight": false,
"sparse_infer": false
},
"quantization": {
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null,
"dataset_columns": null,
"dataset_name": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_subset": null,
"do_quantization": false,
"quant_img_RGB2BGR": false,
"quantized_algorithm": "normal",
"quantized_dtype": "w8a8",
"quantized_hybrid_level": 0,
"quantized_method": "channel"
},
"rktransformers_version": "0.3.1",
"single_core_mode": false,
"std_values": null,
"target_platform": "rk3588",
"task": "feature-extraction",
"task_kwargs": null
},
"model_b1_s1024.rknn": {
"batch_size": 1,
"custom_string": null,
"dynamic_input": null,
"float_dtype": "float16",
"inputs_yuv_fmt": null,
"max_seq_length": 1024,
"mean_values": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"opset": 19,
"optimization": {
"compress_weight": false,
"enable_flash_attention": true,
"model_pruning": false,
"optimization_level": 0,
"remove_reshape": false,
"remove_weight": false,
"sparse_infer": false
},
"quantization": {
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null,
"dataset_columns": null,
"dataset_name": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_subset": null,
"do_quantization": false,
"quant_img_RGB2BGR": false,
"quantized_algorithm": "normal",
"quantized_dtype": "w8a8",
"quantized_hybrid_level": 0,
"quantized_method": "channel"
},
"rktransformers_version": "0.3.1",
"single_core_mode": false,
"std_values": null,
"target_platform": "rk3588",
"task": "feature-extraction",
"task_kwargs": null
},
"model_b1_s256.rknn": {
"batch_size": 1,
"custom_string": null,
"dynamic_input": null,
"float_dtype": "float16",
"inputs_yuv_fmt": null,
"max_seq_length": 256,
"mean_values": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"opset": 19,
"optimization": {
"compress_weight": false,
"enable_flash_attention": true,
"model_pruning": false,
"optimization_level": 0,
"remove_reshape": false,
"remove_weight": false,
"sparse_infer": false
},
"quantization": {
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null,
"dataset_columns": null,
"dataset_name": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_subset": null,
"do_quantization": false,
"quant_img_RGB2BGR": false,
"quantized_algorithm": "normal",
"quantized_dtype": "w8a8",
"quantized_hybrid_level": 0,
"quantized_method": "channel"
},
"rktransformers_version": "0.3.1",
"single_core_mode": false,
"std_values": null,
"target_platform": "rk3588",
"task": "feature-extraction",
"task_kwargs": null
},
"rknn/model_b1_s1024_o1.rknn": {
"batch_size": 1,
"custom_string": null,
"dynamic_input": null,
"float_dtype": "float16",
"inputs_yuv_fmt": null,
"max_seq_length": 1024,
"mean_values": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"opset": 19,
"optimization": {
"compress_weight": false,
"enable_flash_attention": true,
"model_pruning": false,
"optimization_level": 1,
"remove_reshape": false,
"remove_weight": false,
"sparse_infer": false
},
"quantization": {
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null,
"dataset_columns": null,
"dataset_name": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_subset": null,
"do_quantization": false,
"quant_img_RGB2BGR": false,
"quantized_algorithm": "normal",
"quantized_dtype": "w8a8",
"quantized_hybrid_level": 0,
"quantized_method": "channel"
},
"rktransformers_version": "0.3.1",
"single_core_mode": false,
"std_values": null,
"target_platform": "rk3588",
"task": "feature-extraction",
"task_kwargs": null
},
"rknn/model_b1_s1024_o2.rknn": {
"batch_size": 1,
"custom_string": null,
"dynamic_input": null,
"float_dtype": "float16",
"inputs_yuv_fmt": null,
"max_seq_length": 1024,
"mean_values": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"opset": 19,
"optimization": {
"compress_weight": false,
"enable_flash_attention": true,
"model_pruning": false,
"optimization_level": 2,
"remove_reshape": false,
"remove_weight": false,
"sparse_infer": false
},
"quantization": {
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null,
"dataset_columns": null,
"dataset_name": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_subset": null,
"do_quantization": false,
"quant_img_RGB2BGR": false,
"quantized_algorithm": "normal",
"quantized_dtype": "w8a8",
"quantized_hybrid_level": 0,
"quantized_method": "channel"
},
"rktransformers_version": "0.3.1",
"single_core_mode": false,
"std_values": null,
"target_platform": "rk3588",
"task": "feature-extraction",
"task_kwargs": null
},
"rknn/model_b1_s1024_o3.rknn": {
"batch_size": 1,
"custom_string": null,
"dynamic_input": null,
"float_dtype": "float16",
"inputs_yuv_fmt": null,
"max_seq_length": 1024,
"mean_values": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"opset": 19,
"optimization": {
"compress_weight": false,
"enable_flash_attention": true,
"model_pruning": false,
"optimization_level": 3,
"remove_reshape": false,
"remove_weight": false,
"sparse_infer": false
},
"quantization": {
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null,
"dataset_columns": null,
"dataset_name": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_subset": null,
"do_quantization": false,
"quant_img_RGB2BGR": false,
"quantized_algorithm": "normal",
"quantized_dtype": "w8a8",
"quantized_hybrid_level": 0,
"quantized_method": "channel"
},
"rktransformers_version": "0.3.1",
"single_core_mode": false,
"std_values": null,
"target_platform": "rk3588",
"task": "feature-extraction",
"task_kwargs": null
},
"rknn/model_b1_s1024_w8a8.rknn": {
"batch_size": 1,
"custom_string": null,
"dynamic_input": null,
"float_dtype": "float16",
"inputs_yuv_fmt": null,
"max_seq_length": 1024,
"mean_values": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"opset": 19,
"optimization": {
"compress_weight": false,
"enable_flash_attention": true,
"model_pruning": false,
"optimization_level": 0,
"remove_reshape": false,
"remove_weight": false,
"sparse_infer": false
},
"quantization": {
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null,
"dataset_columns": [
"answer"
],
"dataset_name": "sentence-transformers/natural-questions",
"dataset_size": 256,
"dataset_split": [
"train"
],
"dataset_subset": null,
"do_quantization": true,
"quant_img_RGB2BGR": false,
"quantized_algorithm": "normal",
"quantized_dtype": "w8a8",
"quantized_hybrid_level": 0,
"quantized_method": "channel"
},
"rktransformers_version": "0.3.1",
"single_core_mode": false,
"std_values": null,
"target_platform": "rk3588",
"task": "feature-extraction",
"task_kwargs": null
},
"rknn/model_o1.rknn": {
"batch_size": 1,
"custom_string": null,
"dynamic_input": null,
"float_dtype": "float16",
"inputs_yuv_fmt": null,
"max_seq_length": 512,
"mean_values": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"opset": 19,
"optimization": {
"compress_weight": false,
"enable_flash_attention": true,
"model_pruning": false,
"optimization_level": 1,
"remove_reshape": false,
"remove_weight": false,
"sparse_infer": false
},
"quantization": {
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null,
"dataset_columns": null,
"dataset_name": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_subset": null,
"do_quantization": false,
"quant_img_RGB2BGR": false,
"quantized_algorithm": "normal",
"quantized_dtype": "w8a8",
"quantized_hybrid_level": 0,
"quantized_method": "channel"
},
"rktransformers_version": "0.3.1",
"single_core_mode": false,
"std_values": null,
"target_platform": "rk3588",
"task": "feature-extraction",
"task_kwargs": null
},
"rknn/model_o2.rknn": {
"batch_size": 1,
"custom_string": null,
"dynamic_input": null,
"float_dtype": "float16",
"inputs_yuv_fmt": null,
"max_seq_length": 512,
"mean_values": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"opset": 19,
"optimization": {
"compress_weight": false,
"enable_flash_attention": true,
"model_pruning": false,
"optimization_level": 2,
"remove_reshape": false,
"remove_weight": false,
"sparse_infer": false
},
"quantization": {
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null,
"dataset_columns": null,
"dataset_name": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_subset": null,
"do_quantization": false,
"quant_img_RGB2BGR": false,
"quantized_algorithm": "normal",
"quantized_dtype": "w8a8",
"quantized_hybrid_level": 0,
"quantized_method": "channel"
},
"rktransformers_version": "0.3.1",
"single_core_mode": false,
"std_values": null,
"target_platform": "rk3588",
"task": "feature-extraction",
"task_kwargs": null
},
"rknn/model_o3.rknn": {
"batch_size": 1,
"custom_string": null,
"dynamic_input": null,
"float_dtype": "float16",
"inputs_yuv_fmt": null,
"max_seq_length": 512,
"mean_values": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"opset": 19,
"optimization": {
"compress_weight": false,
"enable_flash_attention": true,
"model_pruning": false,
"optimization_level": 3,
"remove_reshape": false,
"remove_weight": false,
"sparse_infer": false
},
"quantization": {
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null,
"dataset_columns": null,
"dataset_name": null,
"dataset_size": 128,
"dataset_split": null,
"dataset_subset": null,
"do_quantization": false,
"quant_img_RGB2BGR": false,
"quantized_algorithm": "normal",
"quantized_dtype": "w8a8",
"quantized_hybrid_level": 0,
"quantized_method": "channel"
},
"rktransformers_version": "0.3.1",
"single_core_mode": false,
"std_values": null,
"target_platform": "rk3588",
"task": "feature-extraction",
"task_kwargs": null
},
"rknn/model_w8a8.rknn": {
"batch_size": 1,
"custom_string": null,
"dynamic_input": null,
"float_dtype": "float16",
"inputs_yuv_fmt": null,
"max_seq_length": 512,
"mean_values": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"opset": 19,
"optimization": {
"compress_weight": false,
"enable_flash_attention": true,
"model_pruning": false,
"optimization_level": 0,
"remove_reshape": false,
"remove_weight": false,
"sparse_infer": false
},
"quantization": {
"auto_hybrid_cos_thresh": 0.98,
"auto_hybrid_euc_thresh": null,
"dataset_columns": [
"answer"
],
"dataset_name": "sentence-transformers/natural-questions",
"dataset_size": 256,
"dataset_split": [
"train"
],
"dataset_subset": null,
"do_quantization": true,
"quant_img_RGB2BGR": false,
"quantized_algorithm": "normal",
"quantized_dtype": "w8a8",
"quantized_hybrid_level": 0,
"quantized_method": "channel"
},
"rktransformers_version": "0.3.1",
"single_core_mode": false,
"std_values": null,
"target_platform": "rk3588",
"task": "feature-extraction",
"task_kwargs": null
}
},
"sep_token_id": 50282,
"sparse_pred_ignore_index": -100,
"sparse_prediction": false,
"torch_dtype": "float32",
"transformers_version": "4.55.4",
"vocab_size": 50368
}