{ "_commit_hash": null, "_name_or_path": "./distilbert-marian-training", "architectures": [ "EncoderDecoderModel" ], "decoder": { "_name_or_path": "Helsinki-NLP/opus-mt-en-nl", "_num_labels": 3, "activation_dropout": 0.0, "activation_function": "swish", "add_bias_logits": false, "add_cross_attention": true, "add_final_layer_norm": false, "architectures": [ "MarianMTModel" ], "attention_dropout": 0.0, "bad_words_ids": [ [ 67027 ] ], "bos_token_id": 0, "chunk_size_feed_forward": 0, "classif_dropout": 0.0, "classifier_dropout": 0.0, "cross_attention_hidden_size": null, "d_model": 512, "decoder_attention_heads": 8, "decoder_ffn_dim": 2048, "decoder_layerdrop": 0.0, "decoder_layers": 6, "decoder_start_token_id": 67027, "decoder_vocab_size": 67028, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.1, "early_stopping": false, "encoder_attention_heads": 8, "encoder_ffn_dim": 2048, "encoder_layerdrop": 0.0, "encoder_layers": 6, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 0, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": 0, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "init_std": 0.02, "is_decoder": true, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "length_penalty": 1.0, "max_length": 512, "max_position_embeddings": 512, "min_length": 0, "model_type": "marian", "no_repeat_ngram_size": 0, "normalize_before": false, "normalize_embedding": false, "num_beam_groups": 1, "num_beams": 4, "num_hidden_layers": 6, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 67027, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "scale_embedding": true, "sep_token_id": null, "share_encoder_decoder_embeddings": true, "static_position_embeddings": true, "task_specific_params": null, "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": null, "torchscript": false, "transformers_version": "4.23.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 67028 }, "decoder_start_token_id": 0, "encoder": { "_name_or_path": "distilbert-base-uncased", "activation": "gelu", "add_cross_attention": false, "architectures": [ "DistilBertForMaskedLM" ], "attention_dropout": 0.1, "bad_words_ids": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "dim": 768, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.1, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_dim": 3072, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 512, "min_length": 0, "model_type": "distilbert", "n_heads": 12, "n_layers": 6, "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": 0, "prefix": null, "problem_type": null, "pruned_heads": {}, "qa_dropout": 0.1, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_weights_": true, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.23.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "vocab_size": 30522 }, "is_encoder_decoder": true, "max_length": 512, "model_type": "encoder-decoder", "pad_token_id": 0, "torch_dtype": "float32", "transformers_version": null }