{
  "_name_or_path": "data/PLMs/longformer-roberta",
  "architectures": [
    "LongformerForMaskedLM"
  ],
  "attention_mode": "longformer",
  "attention_probs_dropout_prob": 0.1,
  "attention_window": [
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128
  ],
  "bos_token_id": 0,
  "classifier_dropout": null,
  "cls_token_id": 0,
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "ignore_attention_mask": false,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 4099,
  "max_sentence_length": 128,
  "max_sentence_size": 128,
  "max_sentences": 8,
  "model_max_length": 4096,
  "model_type": "longformer",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "sep_token_id": 2,
  "torch_dtype": "float32",
  "transformers_version": "4.18.0",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 50265
}