| { | |
| "architectures": [ | |
| "MT5ForConditionalGeneration" | |
| ], | |
| "d_ff": 1024, | |
| "d_kv": 64, | |
| "d_model": 512, | |
| "decoder_start_token_id": 101, | |
| "dropout_rate": 0.0, | |
| "feed_forward_proj": "gated-gelu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "mt5", | |
| "n_positions": 512, | |
| "num_decoder_layers": 8, | |
| "num_heads": 6, | |
| "num_layers": 8, | |
| "pad_token_id": 0, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "BertTokenizer", | |
| "vocab_size": 21228 | |
| } | |