notconfig.json

{
  "_name_or_path": "TC32_HF/model",
  "architectures": [
    "BertModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "backend": "tensorflow",
  "class_name": "Functional",
  "classifier_dropout": null,
  "config": {
    "input_layers": [
      [
        "input_ids",
        0,
        0
      ],
      [
        "attention_mask",
        0,
        0
      ]
    ],
    "layers": [
      {
        "class_name": "InputLayer",
        "config": {
          "batch_input_shape": [
            null,
            256
          ],
          "dtype": "int32",
          "name": "input_ids",
          "ragged": false,
          "sparse": false
        },
        "inbound_nodes": [],
        "name": "input_ids"
      },
      {
        "class_name": "InputLayer",
        "config": {
          "batch_input_shape": [
            null,
            256
          ],
          "dtype": "int32",
          "name": "attention_mask",
          "ragged": false,
          "sparse": false
        },
        "inbound_nodes": [],
        "name": "attention_mask"
      },
      {
        "class_name": "Custom>TFBertMainLayer",
        "config": {
          "config": {
            "_name_or_path": "dbmdz/bert-base-turkish-128k-cased",
            "add_cross_attention": false,
            "architectures": null,
            "attention_probs_dropout_prob": 0.1,
            "bad_words_ids": null,
            "begin_suppress_tokens": null,
            "bos_token_id": null,
            "chunk_size_feed_forward": 0,
            "classifier_dropout": null,
            "cross_attention_hidden_size": null,
            "decoder_start_token_id": null,
            "diversity_penalty": 0.0,
            "do_sample": false,
            "early_stopping": false,
            "encoder_no_repeat_ngram_size": 0,
            "eos_token_id": null,
            "exponential_decay_length_penalty": null,
            "finetuning_task": null,
            "forced_bos_token_id": null,
            "forced_eos_token_id": null,
            "hidden_act": "gelu",
            "hidden_dropout_prob": 0.1,
            "hidden_size": 768,
            "id2label": {
              "0": "LABEL_0",
              "1": "LABEL_1"
            },
            "initializer_range": 0.02,
            "intermediate_size": 3072,
            "is_decoder": false,
            "is_encoder_decoder": false,
            "label2id": {
              "LABEL_0": 0,
              "LABEL_1": 1
            },
            "layer_norm_eps": 1e-12,
            "length_penalty": 1.0,
            "max_length": 20,
            "max_position_embeddings": 512,
            "min_length": 0,
            "model_type": "bert",
            "no_repeat_ngram_size": 0,
            "num_attention_heads": 12,
            "num_beam_groups": 1,
            "num_beams": 1,
            "num_hidden_layers": 12,
            "num_return_sequences": 1,
            "output_attentions": false,
            "output_hidden_states": false,
            "output_scores": false,
            "pad_token_id": 0,
            "position_embedding_type": "absolute",
            "prefix": null,
            "problem_type": null,
            "pruned_heads": {},
            "remove_invalid_values": false,
            "repetition_penalty": 1.0,
            "return_dict": true,
            "return_dict_in_generate": false,
            "sep_token_id": null,
            "suppress_tokens": null,
            "task_specific_params": null,
            "temperature": 1.0,
            "tf_legacy_loss": false,
            "tie_encoder_decoder": false,
            "tie_word_embeddings": true,
            "tokenizer_class": null,
            "top_k": 50,
            "top_p": 1.0,
            "torch_dtype": null,
            "torchscript": false,
            "transformers_version": "4.23.1",
            "type_vocab_size": 2,
            "typical_p": 1.0,
            "use_bfloat16": false,
            "use_cache": true,
            "vocab_size": 128000
          },
          "dtype": "float32",
          "name": "bert",
          "trainable": true
        },
        "inbound_nodes": [
          [
            [
              "input_ids",
              0,
              0,
              {
                "attention_mask": [
                  "attention_mask",
                  0,
                  0
                ]
              }
            ]
          ]
        ],
        "name": "bert"
      },
      {
        "class_name": "Dense",
        "config": {
          "activation": "relu",
          "activity_regularizer": null,
          "bias_constraint": null,
          "bias_initializer": {
            "class_name": "Zeros",
            "config": {}
          },
          "bias_regularizer": null,
          "dtype": "float32",
          "kernel_constraint": null,
          "kernel_initializer": {
            "class_name": "GlorotUniform",
            "config": {
              "seed": null
            }
          },
          "kernel_regularizer": null,
          "name": "intermediate_layer",
          "trainable": true,
          "units": 512,
          "use_bias": true
        },
        "inbound_nodes": [
          [
            [
              "bert",
              0,
              1,
              {}
            ]
          ]
        ],
        "name": "intermediate_layer"
      },
      {
        "class_name": "Dense",
        "config": {
          "activation": "softmax",
          "activity_regularizer": null,
          "bias_constraint": null,
          "bias_initializer": {
            "class_name": "Zeros",
            "config": {}
          },
          "bias_regularizer": null,
          "dtype": "float32",
          "kernel_constraint": null,
          "kernel_initializer": {
            "class_name": "GlorotUniform",
            "config": {
              "seed": null
            }
          },
          "kernel_regularizer": null,
          "name": "output_layer",
          "trainable": true,
          "units": 32,
          "use_bias": true
        },
        "inbound_nodes": [
          [
            [
              "intermediate_layer",
              0,
              0,
              {}
            ]
          ]
        ],
        "name": "output_layer"
      }
    ],
    "name": "model",
    "output_layers": [
      [
        "output_layer",
        0,
        0
      ]
    ]
  },
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "keras_version": "2.10.0",
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "transformers_version": "4.23.1",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 30522
}