| { | |
| "architectures": [ | |
| "XLMRobertaXLForEstimation" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_xlm_roberta_xl.XLMRobertaXLConfig", | |
| "AutoModel": "modeling_xlm_roberta_xl.XLMRobertaXLForEstimation" | |
| }, | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "xlm-roberta-xl", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 250880, | |
| "tokenizer_class": "XLMRobertaTokenizer", | |
| "layer_transformation": "softmax", | |
| "layer_norm": true, | |
| "dropout": 0.1, | |
| "estimator_sizes": [2560, 1280] | |
| } | |