| { |
| "add_cross_attention": false, |
| "architectures": [ |
| "BertForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "bos_token_id": null, |
| "classifier_dropout": null, |
| "dtype": "float32", |
| "eos_token_id": null, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 256, |
| "initializer_range": 0.02, |
| "intermediate_size": 1024, |
| "is_decoder": false, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 256, |
| "model_type": "bert", |
| "num_attention_heads": 4, |
| "num_hidden_layers": 4, |
| "pad_token_id": 0, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.1.0", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 32000 |
| } |
|
|
