| { |
| "architectures": [ |
| "XLMRobertaForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "bos_token_id": 0, |
| "eos_token_id": 2, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 514, |
| "model_type": "xlm-roberta", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 24, |
| "output_past": true, |
| "pad_token_id": 1, |
| "position_embedding_type": "absolute", |
| "transformers_version": "4.17.0.dev0", |
| "type_vocab_size": 1, |
| "use_cache": true, |
| "vocab_size": 250002, |
| "estimator_hidden_sizes": [ |
| 3072, |
| 1024 |
| ], |
| "estimator_activations": "Tanh", |
| "estimator_final_activation": null, |
| "max_len": 512 |
| } |
