| { | |
| "architectures": [ | |
| "PlbertForPreTraining" | |
| ], | |
| "vocab_size": 171, | |
| "embedding_size": 768, | |
| "hidden_size": 768, | |
| "output_size": 768, | |
| "intermediate_size": 3072, | |
| "max_position_embeddings": 1024, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "hidden_act": "gelu", | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_dropout_prob": 0.1, | |
| "layer_norm_eps": 1e-12, | |
| "initializer_range": 0.02, | |
| "pad_token_id": 0, | |
| "position_biased_input": false, | |
| "position_embedding_type": "relative_key_query", | |
| "use_sup_phoneme": false, | |
| "sup_phoneme_vocab_size": 30000, | |
| "grapheme_max_position_embeddings": 1024, | |
| "grapheme_vocab_size": 84481, | |
| "use_cache": false, | |
| "gradient_checkpointing": false, | |
| "transformers_version": "4.41.2" | |
| } | |