config.json

{
  "_name_or_path": "yhavinga/t5-small-24L-ccmatrix-multi",
  "architectures": [
    "T5ForSequenceClassification"
  ],
  "classifier_dropout": 0.0,
  "d_ff": 1920,
  "d_kv": 64,
  "d_model": 512,
  "decoder_start_token_id": 0,
  "dense_act_fn": "gelu_new",
  "dropout_rate": 0.0,
  "early_stopping": true,
  "eos_token_id": 1,
  "feed_forward_proj": "gated-gelu",
  "id2label": {
    "0": "NO_CS",
    "1": "CS"
  },
  "initializer_factor": 1.0,
  "is_encoder_decoder": true,
  "is_gated_act": true,
  "label2id": {
    "CS": 1,
    "NO_CS": 0
  },
  "layer_norm_epsilon": 1e-06,
  "max_length": 128,
  "model_type": "t5",
  "num_beams": 4,
  "num_decoder_layers": 24,
  "num_heads": 8,
  "num_layers": 24,
  "output_past": true,
  "pad_token_id": 0,
  "prefix": "translate English to Dutch: ",
  "problem_type": "single_label_classification",
  "relative_attention_max_distance": 128,
  "relative_attention_num_buckets": 32,
  "task_specific_params": {
    "translation_en_to_nl": {
      "early_stopping": true,
      "max_length": 128,
      "num_beams": 4,
      "prefix": "translate English to Dutch: "
    },
    "translation_nl_to_en": {
      "early_stopping": true,
      "max_length": 128,
      "num_beams": 4,
      "prefix": "translate Dutch to English: "
    }
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.40.0",
  "use_cache": true,
  "vocab_size": 32103
}