{ "auxiliary_encoder_heads": null, "encoder_head_dropout": 0.2, "encoder_head_layers": [ 2048, 1024 ], "random_weights": false, "scalars_prediction_head": { "dropout": 0.0, "layers": [], "num_classes": 1 }, "support_input_scalars": true, "t5_config": { "_name_or_path": "/home/patrick/hugging_face/t5/t5-v1_1-base", "add_cross_attention": false, "architectures": [ "T5ForConditionalGeneration" ], "attention_scale": null, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "classifier_dropout": 0.0, "cross_attention_hidden_size": null, "d_ff": 2048, "d_kv": 64, "d_model": 768, "decoder_start_token_id": 16, "dense_act_fn": "gelu_new", "diversity_penalty": 0.0, "do_sample": false, "dropout_rate": 0.1, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 5, "exponential_decay_length_penalty": null, "feed_forward_proj": "gated-gelu", "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_factor": 1.0, "is_decoder": false, "is_encoder_decoder": true, "is_gated_act": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_epsilon": 1e-06, "length_penalty": 1.0, "mask_token_id": 4, "max_length": 20, "memory_efficient_attention": null, "min_length": 0, "model_type": "t5", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_decoder_layers": 12, "num_heads": 12, "num_layers": 12, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_past": true, "output_scores": false, "pad_token_id": 1, "position_embedding_definitions": { "default": { "config": null, "type": "t5_default_relative" } }, "prefix": null, "problem_type": null, "pruned_heads": {}, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 32, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "support_scalars": false, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 100001 }, "transformers_version": "4.43.4", "use_lora": false }