config.json

{
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "architectures": [
    "MarianMTModel"
  ],
  "attention_dropout": 0.0,
  "d_ff": 3072,
  "d_kv": 64,
  "d_model": 768,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 0,
  "decoder_vocab_size": 32128,
  "dropout": 0.1,
  "dropout_rate": 0.1,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 1,
  "forced_eos_token_id": 0,
  "init_std": 0.02,
  "initializer_factor": 1.0,
  "is_encoder_decoder": true,
  "layer_norm_epsilon": 1e-06,
  "max_position_embeddings": 1024,
  "model_type": "marian",
  "n_positions": 512,
  "num_heads": 12,
  "num_hidden_layers": 12,
  "num_layers": 12,
  "output_past": true,
  "pad_token_id": 0,
  "relative_attention_num_buckets": 32,
  "scale_embedding": false,
  "share_encoder_decoder_embeddings": 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: "
    }
  },
  "torch_dtype": "float32",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "vocab_size": 32128
}