config.json

{
  "architectures": [
    "GraphNystromformerForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.2,
  "attention_window": 200,
  "block_size": 20,
  "bos_token_id": -1,
  "classifier_dropout": 0.2,
  "conv_kernel_size": 65,
  "eos_token_id": -1,
  "hidden_act": "relu",
  "hidden_dropout_prob": 0.2,
  "hidden_size": 240,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4",
    "5": "LABEL_5",
    "6": "LABEL_6"
  },
  "initializer_range": 0.02,
  "intermediate_size": 720,
  "inv_coeff_init_option": false,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4,
    "LABEL_5": 5,
    "LABEL_6": 6
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 35000,
  "model_type": "graph_nystromformer",
  "num_attention_heads": 6,
  "num_hidden_layers": 3,
  "num_landmarks": 64,
  "num_random_blocks": 3,
  "pad_token_id": 0,
  "position_embedding_type": "default",
  "problem_type": "single_label_classification",
  "rescale_embeddings": false,
  "segment_means_seq_len": 64,
  "sep_token_id": -1,
  "torch_dtype": "float32",
  "transformers_version": "4.20.1",
  "type_vocab_size": 2,
  "use_bias": true,
  "use_cache": false,
  "vocab_size": 497
}