config.json

{
  "_name_or_path": "t5-base",
  "architectures": [
    "BertForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "d_ff": 3072,
  "d_kv": 64,
  "d_model": 768,
  "decoder_start_token_id": 0,
  "dropout_rate": 0.1,
  "eos_token_id": 1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "Skill",
    "1": "Exp",
    "2": "PI",
    "3": "Sum",
    "4": "Edu",
    "5": "Obj",
    "6": "QC"
  },
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "is_encoder_decoder": true,
  "label2id": {
    "Edu": 4,
    "Exp": 1,
    "Obj": 5,
    "PI": 2,
    "QC": 6,
    "Skill": 0,
    "Sum": 3
  },
  "layer_norm_eps": 1e-12,
  "layer_norm_epsilon": 1e-06,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "n_positions": 512,
  "num_attention_heads": 12,
  "num_heads": 12,
  "num_hidden_layers": 12,
  "num_layers": 12,
  "output_past": true,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "problem_type": "single_label_classification",
  "relative_attention_num_buckets": 32,
  "task_specific_params": {
    "summarization": {
      "early_stopping": true,
      "length_penalty": 2.0,
      "max_length": 200,
      "min_length": 30,
      "no_repeat_ngram_size": 3,
      "num_beams": 4,
      "prefix": "summarize: "
    },
    "translation_en_to_de": {
      "early_stopping": true,
      "max_length": 300,
      "num_beams": 4,
      "prefix": "translate English to German: "
    },
    "translation_en_to_fr": {
      "early_stopping": true,
      "max_length": 300,
      "num_beams": 4,
      "prefix": "translate English to French: "
    },
    "translation_en_to_ro": {
      "early_stopping": true,
      "max_length": 300,
      "num_beams": 4,
      "prefix": "translate English to Romanian: "
    }
  },
  "torch_dtype": "float32",
  "transformers_version": "4.38.2",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 32128
}