config.json

{
  "_num_labels": 3,
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "add_bias_logits": false,
  "add_final_layer_norm": true,
  "architectures": [
    "MLongformerEncoderDecoderForConditionalGenerationCustom"
  ],
  "attention_dilation": [
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1
  ],
  "attention_dropout": 0.0,
  "attention_mode": "sliding_chunks",
  "attention_probs_dropout_prob": 0.0,
  "attention_window": [
    512,
    512,
    512,
    512,
    512,
    512,
    512,
    512,
    512,
    512,
    512,
    512
  ],
  "auto_map": {
    "AutoConfig": "longformer_enc_dec_custom.MLongformerEncoderDecoderConfigCustom",
    "AutoModelForSeq2SeqLM": "longformer_enc_dec_custom.MLongformerEncoderDecoderForConditionalGenerationCustom"
  },
  "autoregressive": false,
  "bos_token_id": 0,
  "classif_dropout": 0.0,
  "classifier_dropout": 0.0,
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_config": {
    "_name_or_path": "josh-oo/german-gpt2-easy",
    "activation_function": "gelu_new",
    "add_cross_attention": true,
    "architectures": [
      "GPT2LMHeadModel"
    ],
    "attn_pdrop": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 50267,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "embd_pdrop": 0.1,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 50266,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "gradient_checkpointing": false,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "is_decoder": true,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_epsilon": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "gpt2",
    "n_ctx": 1024,
    "n_embd": 768,
    "n_head": 12,
    "n_inner": null,
    "n_layer": 12,
    "n_positions": 1024,
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 50268,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "reorder_and_upcast_attn": false,
    "repetition_penalty": 1.0,
    "resid_pdrop": 0.1,
    "return_dict": true,
    "return_dict_in_generate": false,
    "scale_attn_by_inverse_layer_idx": false,
    "scale_attn_weights": true,
    "sep_token_id": null,
    "summary_activation": null,
    "summary_first_dropout": 0.1,
    "summary_proj_to_labels": true,
    "summary_type": "cls_index",
    "summary_use_proj": true,
    "suppress_tokens": null,
    "task_specific_params": {
      "text-generation": {
        "do_sample": true,
        "max_length": 50
      }
    },
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "float32",
    "torchscript": false,
    "transformers_version": "4.29.2",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 50269
  },
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "dropout": 0.1,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 50266,
  "forced_eos_token_id": 2,
  "from_mbart": false,
  "global_attention_indices": [
    -1
  ],
  "gradient_checkpointing": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "max_decoder_position_embeddings": 1024,
  "max_encoder_position_embeddings": 4096,
  "max_length": 1024,
  "max_position_embeddings": 1024,
  "model_type": "mbart",
  "normalize_before": true,
  "normalize_embedding": true,
  "num_beams": 5,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 1,
  "scale_embedding": true,
  "static_position_embeddings": false,
  "task_specific_params": {
    "translation_en_to_ro": {
      "decoder_start_token_id": 250020
    }
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.29.2",
  "use_cache": true,
  "vocab_size": 20031
}