{
  "activation_fn": "gelu",
  "architectures": [
    "ITER"
  ],
  "d_ff": 3072,
  "d_model": 768,
  "dataset": "label_studio",
  "dropout": 0.3,
  "features": 10752,
  "max_length": 512,
  "max_nest_depth": 5,
  "model_type": "UwU",
  "num_links": 21,
  "num_types": 8,
  "torch_dtype": "float32",
  "transformer_config": {
    "_name_or_path": "t5-base",
    "architectures": [
      "T5ForConditionalGeneration"
    ],
    "d_ff": 3072,
    "d_model": 768,
    "decoder_start_token_id": 0,
    "max_length": 512,
    "model_type": "t5",
    "n_positions": 512,
    "num_decoder_layers": 12,
    "num_heads": 12,
    "num_layers": 12,
    "output_past": true,
    "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: "
      }
    }
  },
  "transformers_version": "4.38.2"
}