| { |
| "architectures": [ |
| "CESAR" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "bert_model": "bert-large-uncased", |
| "causal_attention": true, |
| "classifier_dropout": null, |
| "gradient_checkpointing": false, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "cesar", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 24, |
| "output_hidden_states": true, |
| "pad_token_id": 0, |
| "position_embedding_type": "absolute", |
| "return_inner_scores": true, |
| "torch_dtype": "float32", |
| "transformers_version": "4.45.2", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 30522 |
| } |
|
|
