{
  "_name_or_path": "/home/user1-system11/Documents/research-shradha/deploy-spt-code/spt-code/outputs/pre_train_20241125_001741/models",
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "architectures": [
    "BartModel"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "classifier_dropout": 0.0,
  "d_model": 768,
  "decoder_attention_heads": 12,
  "decoder_ffn_dim": 3072,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 1,
  "dropout": 0.1,
  "encoder_attention_heads": 12,
  "encoder_ffn_dim": 3072,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 2,
  "forced_eos_token_id": 2,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "max_length": 256,
  "max_position_embeddings": 1024,
  "min_length": 1,
  "model_type": "bart",
  "num_beams": 5,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "scale_embedding": false,
  "torch_dtype": "float32",
  "transformers_version": "4.36.2",
  "use_cache": true,
  "vocab_size": 80059
}