| { | |
| "architectures": [ | |
| "MT5ForConditionalGeneration" | |
| ], | |
| "classifier_dropout": 0.0, | |
| "d_ff": 512, | |
| "d_kv": 64, | |
| "d_model": 256, | |
| "decoder_start_token_id": 2, | |
| "decoder_vocab_size": 137, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "encoder_vocab_size": 822, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "mt5", | |
| "num_decoder_layers": 4, | |
| "num_heads": 3, | |
| "num_layers": 4, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "shared_embedding": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "T5Tokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.37.1", | |
| "use_cache": true | |
| } | |