| { | |
| "architectures": [ | |
| "T5ForZeroShotClassification" | |
| ], | |
| "classifier_dropout": 0.0, | |
| "d_ff": 2048, | |
| "d_kv": 64, | |
| "d_model": 768, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "encoder_attention_type": "block", | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "global_block_size": 128, | |
| "id2label": { | |
| "0": "contradiction", | |
| "1": "entailment", | |
| "2": "neutral" | |
| }, | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "label2id": { | |
| "contradiction": 0, | |
| "entailment": 1, | |
| "neutral": 2 | |
| }, | |
| "layer_norm_epsilon": 1e-06, | |
| "loss_type": "cross_entropy", | |
| "model_type": "T5", | |
| "naive_attention": true, | |
| "num_decoder_layers": 12, | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "positional_embedding_type": "relative", | |
| "problem_type": "single_label_classification", | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "residuals": "pre", | |
| "sliding_window": 128, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "T5Tokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.33.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 250112 | |
| } | |